AI and science frontiers · 2026-11-16

Nonlinear time-optimal model predictive control (TOMPC) drives constrained systems to a target in minimum time, but online solving is too slow for fast dynamics. This work imitates a long-horizon, nonconvex TOMPC with hard terminal constraints using a neural network, and introduces self-informed sampling: the network also predicts time-to-go, and the expert solver is queried only where a rollout departs from time-optimal behavior. On a Furuta pendulum, this sampling reaches the performance of standard dataset aggregation in roughly one-third of the training time and less than half the data, while the resulting controller keeps the expert's region of attraction and GPU inference raises the control frequency from about 1.4 Hz to 1 kHz.

Nonlinear time-optimal model predictive control (TOMPC) drives constrained systems to a target in minimum time, but online solving is too slow for fast dynamics. This work imitates a long-horizon, nonconvex TOMPC with hard terminal constraints using a neural network, and introduces self-informed sampling: the network also predicts time-to-go, and the expert solver is queried only where a rollout departs from time-optimal behavior. On a Furuta pendulum, this sampling reaches the performance of standard dataset aggregation in roughly one-third of the training time and less than half the data, while the resulting controller keeps the expert's region of attraction and GPU inference raises the control frequency from about 1.4 Hz to 1 kHz.

Vision-language-action policies process hundreds of visual tokens per step, which drives up inference latency. APS-VLA keeps the backbone frozen and uses a lightweight scorer conditioned on the current observation, instruction and proprioception to pick tokens, training the retained representation both to reproduce policy outputs and to predict the subsequent visual change. On LIBERO with 128 tokens retained, mean success is 95.75%, 1.25 points below the unpruned 97.00%, and inference latency falls to 68.75 ms.

Vision-language-action policies process hundreds of visual tokens per step, which drives up inference latency. APS-VLA keeps the backbone frozen and uses a lightweight scorer conditioned on the current observation, instruction and proprioception to pick tokens, training the retained representation both to reproduce policy outputs and to predict the subsequent visual change. On LIBERO with 128 tokens retained, mean success is 95.75%, 1.25 points below the unpruned 97.00%, and inference latency falls to 68.75 ms.

Multivariate time-series anomaly detection has long relied on graph detectors trained from scratch on limited target-domain data, whose learned sensor topologies are prone to spurious correlations and cannot reuse relational priors from pretrained graph models. Gfm4Mtsad wraps a frozen graph foundation model in three peripheral modules: SICA aligns temporal features with normal-connectivity priors and restores projection-lost detail, MAPS synthesizes near-boundary pseudo-anomalies through residual-preserving local dependency breaks, and TGEC re-ranks multi-granular evidence only in the upper score tail. Across MSL P-15, SMAP T-3 and SMD 1-1 with AnomalyGFM and OwlEye backbones, the adaptation reaches best or second-best results on most metrics.

Multivariate time-series anomaly detection has long relied on graph detectors trained from scratch on limited target-domain data, whose learned sensor topologies are prone to spurious correlations and cannot reuse relational priors from pretrained graph models. Gfm4Mtsad wraps a frozen graph foundation model in three peripheral modules: SICA aligns temporal features with normal-connectivity priors and restores projection-lost detail, MAPS synthesizes near-boundary pseudo-anomalies through residual-preserving local dependency breaks, and TGEC re-ranks multi-granular evidence only in the upper score tail. Across MSL P-15, SMAP T-3 and SMD 1-1 with AnomalyGFM and OwlEye backbones, the adaptation reaches best or second-best results on most metrics.

Hybrid language models compress history into fixed-size recurrent states, yet serving systems still treat those states as dense matrices, reading and rewriting them whole at every decoding step, so memory traffic grows with batch size. SinkState exploits the concentration of queries, keys and values in linear attention into a stable low-dimensional subspace, keeping each state in an adaptive low-rank factorization throughout decoding, merging new tokens with a local SVD and consolidating the frozen part asynchronously on the CPU. Across four Mamba-2 and GDN hybrid models from 4B to 120B parameters, peak recurrent-state memory falls to 0.38–0.63 of the baseline and decoding speeds up by up to 1.58x, with accuracy maintained.

Hybrid language models compress history into fixed-size recurrent states, yet serving systems still treat those states as dense matrices, reading and rewriting them whole at every decoding step, so memory traffic grows with batch size. SinkState exploits the concentration of queries, keys and values in linear attention into a stable low-dimensional subspace, keeping each state in an adaptive low-rank factorization throughout decoding, merging new tokens with a local SVD and consolidating the frozen part asynchronously on the CPU. Across four Mamba-2 and GDN hybrid models from 4B to 120B parameters, peak recurrent-state memory falls to 0.38–0.63 of the baseline and decoding speeds up by up to 1.58x, with accuracy maintained.

In contact-rich manipulation, expert demonstrations cover successful paths but say little about how force responds to different actions, while task-agnostic play records broader contact dynamics without a task goal. ForceWAM gives the task-compatible motion and six-axis force/torque future to a force world model trained on demonstrations, and gives the question of which actions realize that future to an inverse dynamics model trained on both demonstrations and play; at deployment, fresh wrench feedback corrects actions between world-model updates. Across force-regulated sliding, box flipping with and without disturbances, and ring placement, the full system reaches 85%, 95%, 85%, and 90% success, above the listed baselines.

In contact-rich manipulation, expert demonstrations cover successful paths but say little about how force responds to different actions, while task-agnostic play records broader contact dynamics without a task goal. ForceWAM gives the task-compatible motion and six-axis force/torque future to a force world model trained on demonstrations, and gives the question of which actions realize that future to an inverse dynamics model trained on both demonstrations and play; at deployment, fresh wrench feedback corrects actions between world-model updates. Across force-regulated sliding, box flipping with and without disturbances, and ring placement, the full system reaches 85%, 95%, 85%, and 90% success, above the listed baselines.

Edge LLM weight formats spend equal bits on every integer code, although the codes are far from uniform. LazyWeights keeps llama.cpp's GGUF formats, tunes GPTQ so the codes concentrate, Huffman-codes them losslessly in 32 interleaved lanes, and decodes them on demand in a small unit between DRAM and L2, leaving GPU kernels unchanged. At 1% and 3.5% perplexity budgets, coded Phi-3-mini, Mistral-7B and SmolLM-1.7B are 5.7–31.4% smaller than the best llama.cpp format; on a Jetson Orin Nano Super, with the decoder unit, latency and energy per token fall by up to 36% and 38%.

Edge LLM weight formats spend equal bits on every integer code, although the codes are far from uniform. LazyWeights keeps llama.cpp's GGUF formats, tunes GPTQ so the codes concentrate, Huffman-codes them losslessly in 32 interleaved lanes, and decodes them on demand in a small unit between DRAM and L2, leaving GPU kernels unchanged. At 1% and 3.5% perplexity budgets, coded Phi-3-mini, Mistral-7B and SmolLM-1.7B are 5.7–31.4% smaller than the best llama.cpp format; on a Jetson Orin Nano Super, with the decoder unit, latency and energy per token fall by up to 36% and 38%.

Multivariate time series anomaly detection has long leaned on reconstruction residuals, but a residual only certifies that a window can be reproduced, not that its channels still explain one another as they do under normal operation. CLOSURE splits recoverability and cross-channel consistency into two prediction tasks trained separately on normal data: a diffusion reconstructor conditioned on a discrete memory of normal temporal bases scores the first, and a relation operator that predicts each channel only from its peers scores the second, with the two combined after calibration on normal data. Across the five public benchmarks SMD, MSL, SMAP, SWaT and PSM, its Aff-F1 exceeds the listed methods, reaching 88.13 on SMD.

Multivariate time series anomaly detection has long leaned on reconstruction residuals, but a residual only certifies that a window can be reproduced, not that its channels still explain one another as they do under normal operation. CLOSURE splits recoverability and cross-channel consistency into two prediction tasks trained separately on normal data: a diffusion reconstructor conditioned on a discrete memory of normal temporal bases scores the first, and a relation operator that predicts each channel only from its peers scores the second, with the two combined after calibration on normal data. Across the five public benchmarks SMD, MSL, SMAP, SWaT and PSM, its Aff-F1 exceeds the listed methods, reaching 88.13 on SMD.

Decision models are usually judged by how well they act, yet the same models are pulled toward an easier subgoal when acting on ALFWorld. Used instead as a teacher that sees the whole trajectory after an episode and is asked whether each action helped, JEV raises a Qwen2.5-1.5B policy trained with GRPO from 72.8% to 82.9% success on ALFWorld and from 56.8% to 71.4% on WebShop, while JEV as an actor completes only 42.9% of ALFWorld tasks.

Decision models are usually judged by how well they act, yet the same models are pulled toward an easier subgoal when acting on ALFWorld. Used instead as a teacher that sees the whole trajectory after an episode and is asked whether each action helped, JEV raises a Qwen2.5-1.5B policy trained with GRPO from 72.8% to 82.9% success on ALFWorld and from 56.8% to 71.4% on WebShop, while JEV as an actor completes only 42.9% of ALFWorld tasks.

GaussianRenderFormer replaces the hand-written rasterizer in 3D Gaussian splatting with a transformer: one token per Gaussian, and a view-dependent decoder that turns small patches of camera rays into pixels. Trained on 26,820 Objaverse objects, it reaches 38.08 dB PSNR on 300 unseen objects against renders of the full splat, while rasterizing the same pruned input reaches 44.02 dB; diagnostics point to a view-decoder bottleneck, though under-training is not ruled out.

GaussianRenderFormer replaces the hand-written rasterizer in 3D Gaussian splatting with a transformer: one token per Gaussian, and a view-dependent decoder that turns small patches of camera rays into pixels. Trained on 26,820 Objaverse objects, it reaches 38.08 dB PSNR on 300 unseen objects against renders of the full splat, while rasterizing the same pruned input reaches 44.02 dB; diagnostics point to a view-decoder bottleneck, though under-training is not ruled out.

Near-out-of-distribution (near-OOD) inputs resemble the training classes closely, and existing post-hoc detectors that excel on far-OOD inputs lose that edge here. PLUS does not replace a detector: it uses a sparse autoencoder to pick each class's most active neurons, spans a low-dimensional subspace, and scores an input by that class's whitened Mahalanobis distance, adding the signal to any calibrated base score at one fixed weight. On the ImageNet-1K OpenOOD v1.5 benchmark, near-OOD AUROC improves in all 126 detector-backbone combinations across 18 detectors and seven backbones, while far-OOD performance is broadly maintained, with declines of at most one point where the base score is already near-saturated.

Near-out-of-distribution (near-OOD) inputs resemble the training classes closely, and existing post-hoc detectors that excel on far-OOD inputs lose that edge here. PLUS does not replace a detector: it uses a sparse autoencoder to pick each class's most active neurons, spans a low-dimensional subspace, and scores an input by that class's whitened Mahalanobis distance, adding the signal to any calibrated base score at one fixed weight. On the ImageNet-1K OpenOOD v1.5 benchmark, near-OOD AUROC improves in all 126 detector-backbone combinations across 18 detectors and seven backbones, while far-OOD performance is broadly maintained, with declines of at most one point where the base score is already near-saturated.

In node classification on heterophilic graphs, the step before propagation has stayed fixed by degree normalisation, which acts spectrally as a valley whose zero is set by the normalisation rather than by the data, exactly where dense graphs' eigenvalues accumulate. SpecValley learns the valley's centre, sharpness and flank gains per graph, then feeds an ordinary ChebNet spectral filter. Across six heterophilic benchmarks it matches or exceeds the best published result on four, sits within the confidence interval of the best on Tolokers, and trails on Actor; crossing five aggregators with four filters attributes the gain to aggregation rather than to the downstream filter.

In node classification on heterophilic graphs, the step before propagation has stayed fixed by degree normalisation, which acts spectrally as a valley whose zero is set by the normalisation rather than by the data, exactly where dense graphs' eigenvalues accumulate. SpecValley learns the valley's centre, sharpness and flank gains per graph, then feeds an ordinary ChebNet spectral filter. Across six heterophilic benchmarks it matches or exceeds the best published result on four, sits within the confidence interval of the best on Tolokers, and trails on Actor; crossing five aggregators with four filters attributes the gain to aggregation rather than to the downstream filter.

WaveGen pulls zero-shot speech synthesis back from multi-stage pipelines into a single diffusion model: text produces raw waveform directly, without a neural audio codec, Mel vocoder, VAE latent or duration predictor. Spectral Forcing makes the same model learn a low-resolution spectral trajectory alongside the target waveform trajectory, giving text-speech alignment a structured guide in high-resolution waveform space. Trained in one stage on open Emilia data, the 0.6B-parameter WaveGen reaches WER 1.47 and speaker similarity SIM 0.75 on the Seed-en benchmark.

WaveGen pulls zero-shot speech synthesis back from multi-stage pipelines into a single diffusion model: text produces raw waveform directly, without a neural audio codec, Mel vocoder, VAE latent or duration predictor. Spectral Forcing makes the same model learn a low-resolution spectral trajectory alongside the target waveform trajectory, giving text-speech alignment a structured guide in high-resolution waveform space. Trained in one stage on open Emilia data, the 0.6B-parameter WaveGen reaches WER 1.47 and speaker similarity SIM 0.75 on the Seed-en benchmark.

Reasoning vision-language models must hold both multimodal context and a growing reasoning trace in their KV cache, and existing low-rank compression calibrates on static inputs, so its divergence from the dense model grows with generation length. TraceKV instead calibrates on reasoning traces the dense model generates itself, weights each KV state by its sensitivity to policy divergence before the SVD, and allocates ranks globally. Across four models including Qwen2.5-VL-7B, a 70% rank ratio with 4-bit quantization gives 73.41% overall accuracy versus 73.58% for the dense model, with the KV cache reduced 5.64 times.

Reasoning vision-language models must hold both multimodal context and a growing reasoning trace in their KV cache, and existing low-rank compression calibrates on static inputs, so its divergence from the dense model grows with generation length. TraceKV instead calibrates on reasoning traces the dense model generates itself, weights each KV state by its sensitivity to policy divergence before the SVD, and allocates ranks globally. Across four models including Qwen2.5-VL-7B, a 70% rank ratio with 4-bit quantization gives 73.41% overall accuracy versus 73.58% for the dense model, with the KV cache reduced 5.64 times.

For summarization settings such as headlines and previews that must fit an exact character count, Delta estimates the expected character length of the current output inside a masked diffusion language model's denoising loop and dynamically inserts or removes masked positions to steer generation toward the target. It needs no fine-tuning and applies to off-the-shelf LLaDA and Dream. Across the XSum, CNN/DailyMail and arXiv summarization benchmarks, character-length error falls by an order of magnitude relative to the baselines while summary quality stays competitive under automatic and human evaluation.

For summarization settings such as headlines and previews that must fit an exact character count, Delta estimates the expected character length of the current output inside a masked diffusion language model's denoising loop and dynamically inserts or removes masked positions to steer generation toward the target. It needs no fine-tuning and applies to off-the-shelf LLaDA and Dream. Across the XSum, CNN/DailyMail and arXiv summarization benchmarks, character-length error falls by an order of magnitude relative to the baselines while summary quality stays competitive under automatic and human evaluation.

Online conformal risk control has assumed each round's loss arrives immediately and intact, yet real systems delay feedback and can track only a limited number of pending predictions, so some feedback is lost for good. CA-OCRC designs the tracking policy and the prediction sets together: each round draws a random proxy delay, is tracked while capacity allows until its feedback arrives or the proxy delay expires, and a two-level inverse probability weighting compensates for lost feedback. Risk bounds for arbitrary and stochastic delays follow, and optimizing the proxy delay distribution shows that capacity growing only logarithmically in the maximum delay suffices to match the convergence rate of OCRC with unlimited feedback.

Online conformal risk control has assumed each round's loss arrives immediately and intact, yet real systems delay feedback and can track only a limited number of pending predictions, so some feedback is lost for good. CA-OCRC designs the tracking policy and the prediction sets together: each round draws a random proxy delay, is tracked while capacity allows until its feedback arrives or the proxy delay expires, and a two-level inverse probability weighting compensates for lost feedback. Risk bounds for arbitrary and stochastic delays follow, and optimizing the proxy delay distribution shows that capacity growing only logarithmically in the maximum delay suffices to match the convergence rate of OCRC with unlimited feedback.

For quadrotor navigation through unknown clutter, ScanDreamer builds an online 2D scan-memory map from depth images and vehicle pose, and conditions its world model, actor and critic on that map, so imagined rollouts advance the pose over a frozen map and read geodesic progress and wall-contact signals from mapped geometry. Across 1560 test episodes in NVIDIA Isaac Sim spanning unseen layouts and parameter ranges, three seeds average 96.3% success and 3.6% collisions, against 59.6% success and 28.8% collisions for AirDreamer at the same online-interaction budget.

For quadrotor navigation through unknown clutter, ScanDreamer builds an online 2D scan-memory map from depth images and vehicle pose, and conditions its world model, actor and critic on that map, so imagined rollouts advance the pose over a frozen map and read geodesic progress and wall-contact signals from mapped geometry. Across 1560 test episodes in NVIDIA Isaac Sim spanning unseen layouts and parameter ranges, three seeds average 96.3% success and 3.6% collisions, against 59.6% success and 28.8% collisions for AirDreamer at the same online-interaction budget.

Emotional video generation has no single correct target, and fixed fusion of visual, motion and text-alignment rewards captures emotional intent poorly. EmoReward distills reward traces from one completed training run into per-emotion-regime reliability estimates, converts them into bounded weight multipliers, and combines them with current-video instance gates in the next run without updating any reward-model parameters. On HunyuanVideo 1.5 with DanceGRPO, FlowGRPO and SAGE-GRPO, VideoAlign Overall rises under all three algorithms, including SAGE-GRPO with EmoReward moving from -0.8269 to -0.2624.

Emotional video generation has no single correct target, and fixed fusion of visual, motion and text-alignment rewards captures emotional intent poorly. EmoReward distills reward traces from one completed training run into per-emotion-regime reliability estimates, converts them into bounded weight multipliers, and combines them with current-video instance gates in the next run without updating any reward-model parameters. On HunyuanVideo 1.5 with DanceGRPO, FlowGRPO and SAGE-GRPO, VideoAlign Overall rises under all three algorithms, including SAGE-GRPO with EmoReward moving from -0.8269 to -0.2624.

Sage-Taiyi splits scientific discovery into two levels: an object level that searches over a target tree and an idea graph, and a meta level that keeps a revisable cognitive state recording which judgments have evidence and which premises remain untested, then uses it to decide what to investigate next and which method to apply. On Taiyi-Bench, 265 tasks drawn from 50 papers across ten disciplines, it scores 54.0 overall against 47.9 for the strongest baseline, AI Scientist-v2, ranking first on all eight metrics. Five expert-guided collaborations in chemistry, materials and engineering carried some proposals to experimental or computational validation, including a cobalt-catalysed carbonylation model reaction raised from trace amounts to 84% yield.

Sage-Taiyi splits scientific discovery into two levels: an object level that searches over a target tree and an idea graph, and a meta level that keeps a revisable cognitive state recording which judgments have evidence and which premises remain untested, then uses it to decide what to investigate next and which method to apply. On Taiyi-Bench, 265 tasks drawn from 50 papers across ten disciplines, it scores 54.0 overall against 47.9 for the strongest baseline, AI Scientist-v2, ranking first on all eight metrics. Five expert-guided collaborations in chemistry, materials and engineering carried some proposals to experimental or computational validation, including a cobalt-catalysed carbonylation model reaction raised from trace amounts to 84% yield.

Vision-language models lose accuracy when irrelevant images sit beside the target, and the loss persists even when the prompt names the target image, because middle-layer distractor-to-text connections carry the interference into reasoning. Using the single-image prediction as a reference, answer consistency regularization aligns answer distributions with and without distractors on Qwen2.5-VL, raising circular accuracy by an average of 16 percentage points across five perception benchmarks with five distractors while preserving single-image performance.

Vision-language models lose accuracy when irrelevant images sit beside the target, and the loss persists even when the prompt names the target image, because middle-layer distractor-to-text connections carry the interference into reasoning. Using the single-image prediction as a reference, answer consistency regularization aligns answer distributions with and without distractors on Qwen2.5-VL, raising circular accuracy by an average of 16 percentage points across five perception benchmarks with five distractors while preserving single-image performance.

Explanations for video action recognition usually fold spatial appearance and temporal motion into a single saliency map, so a user cannot tell whether the model predicted from the object or from the movement. This work separates the explanation into a spatial appearance mask and a temporal motion mask, optimized jointly against a frozen classifier, with nearest-frame replacement used to remove temporal dynamics. On EPIC-Kitchens-55, EGTEA Gaze+, and Something-Something V2, the method attains the lowest deletion AUC on most datasets and axes, with masks roughly one-fifth the size of the strongest baseline.

Explanations for video action recognition usually fold spatial appearance and temporal motion into a single saliency map, so a user cannot tell whether the model predicted from the object or from the movement. This work separates the explanation into a spatial appearance mask and a temporal motion mask, optimized jointly against a frozen classifier, with nearest-frame replacement used to remove temporal dynamics. On EPIC-Kitchens-55, EGTEA Gaze+, and Something-Something V2, the method attains the lowest deletion AUC on most datasets and axes, with masks roughly one-fifth the size of the strongest baseline.

As feed-forward 3D Gaussian splatting scales to more views, anchor-based compression fixes the decoder-facing representation but lets support-to-anchor fusion grow with view count. CrossPressor leaves released checkpoints untouched and routes support features before K/V projection with coverage-cycled offsets, spreading retained spatial evidence across support views and fusion layers. At 256 views it keeps 1.85% of dense QK interactions, cutting cross-view latency from 125.28 ms to 4.80 ms while rendering quality stays close to dense fusion.

As feed-forward 3D Gaussian splatting scales to more views, anchor-based compression fixes the decoder-facing representation but lets support-to-anchor fusion grow with view count. CrossPressor leaves released checkpoints untouched and routes support features before K/V projection with coverage-cycled offsets, spreading retained spatial evidence across support views and fusion layers. At 256 views it keeps 1.85% of dense QK interactions, cutting cross-view latency from 125.28 ms to 4.80 ms while rendering quality stays close to dense fusion.

Test-time search for multi-step LLM reasoning has long traded between two imperfect signals: post-hoc voting keeps diversity but cannot steer generation toward correct paths, while beam-style verifier guidance intervenes early but over-concentrates and amplifies verifier errors. VGSC multiplies step-level correctness with a future-outcome prediction into an acceptance weight, applies bounded rejection-resampling to candidate steps during decoding, and keeps multiple trajectories for final self-consistency voting. Across five reasoning benchmarks with the Qwen2.5 Math 1.5B Instruct generator and Qwen2.5 Math PRM 7B verifier, VGSC reaches 63.1% average accuracy at verifier-trust exponent 10, above the strongest non-VGSC baseline BS+SC-Future at 60.7%.

Test-time search for multi-step LLM reasoning has long traded between two imperfect signals: post-hoc voting keeps diversity but cannot steer generation toward correct paths, while beam-style verifier guidance intervenes early but over-concentrates and amplifies verifier errors. VGSC multiplies step-level correctness with a future-outcome prediction into an acceptance weight, applies bounded rejection-resampling to candidate steps during decoding, and keeps multiple trajectories for final self-consistency voting. Across five reasoning benchmarks with the Qwen2.5 Math 1.5B Instruct generator and Qwen2.5 Math PRM 7B verifier, VGSC reaches 63.1% average accuracy at verifier-trust exponent 10, above the strongest non-VGSC baseline BS+SC-Future at 60.7%.

Small execution errors in imitation policies accumulate into failure, and earlier fixes relied on additional on-policy learning or costly online planning. A2WM learns local action sensitivity offline from action-perturbed rollouts of a frozen policy, predicting task-relevant geometry as a nominal trajectory plus a linear response to corrections, which turns online refinement into one model evaluation and one convex quadratic program solve. Across four simulated manipulation tasks it reaches the highest mean success among the evaluated baselines, 59.51% versus 27.18% for Diffusion Policy, with 3.8 ms mean refinement overhead per control step excluding base-policy sampling.

Small execution errors in imitation policies accumulate into failure, and earlier fixes relied on additional on-policy learning or costly online planning. A2WM learns local action sensitivity offline from action-perturbed rollouts of a frozen policy, predicting task-relevant geometry as a nominal trajectory plus a linear response to corrections, which turns online refinement into one model evaluation and one convex quadratic program solve. Across four simulated manipulation tasks it reaches the highest mean success among the evaluated baselines, 59.51% versus 27.18% for Diffusion Policy, with 3.8 ms mean refinement overhead per control step excluding base-policy sampling.

In shallow ReLU models, the spectral bias that makes high frequencies learn slowly is tied directly to the condition number of the feature dictionary's Gram matrix. Multiplying each ReLU feature by a hat partition-of-unity weight makes that Gram matrix block-tridiagonal for any local bilinear form, and its block-Toeplitz symbol sets the learning rate of each frequency. Under a regression loss the symbol stays away from zero, and the measured spread of frequency-dependent learning rates falls from four orders of magnitude to within a factor of five at matched model size; under the stiffness matrix the symbol vanishes at zero frequency, so gating leaves conditioning intact and instead makes the lowest frequency the slowest mode.

In shallow ReLU models, the spectral bias that makes high frequencies learn slowly is tied directly to the condition number of the feature dictionary's Gram matrix. Multiplying each ReLU feature by a hat partition-of-unity weight makes that Gram matrix block-tridiagonal for any local bilinear form, and its block-Toeplitz symbol sets the learning rate of each frequency. Under a regression loss the symbol stays away from zero, and the measured spread of frequency-dependent learning rates falls from four orders of magnitude to within a factor of five at matched model size; under the stiffness matrix the symbol vanishes at zero frequency, so gating leaves conditioning intact and instead makes the lowest frequency the slowest mode.

AskALCF, an agentic system for high-performance computing user support, attributes each failed question-answer turn to one of five components—knowledge, retrieval, prompt, model or tools—instead of returning only a quality score. Across 2,174 production support turns it cut unattributable failures from 41.4% to 14.2%, and on a 150-turn expert reference it raised agreement from 108 to 123 turns. The object of improvement is the rules, prompts and review policy rather than model weights, and experts retain authority over every production-facing change.

AskALCF, an agentic system for high-performance computing user support, attributes each failed question-answer turn to one of five components—knowledge, retrieval, prompt, model or tools—instead of returning only a quality score. Across 2,174 production support turns it cut unattributable failures from 41.4% to 14.2%, and on a 150-turn expert reference it raised agreement from 108 to 123 turns. The object of improvement is the rules, prompts and review policy rather than model weights, and experts retain authority over every production-facing change.

In expert-parallel MoE serving, each layer finishes only when its most loaded GPU does, and routing shifts at every decode step. Relief replaces the per-step linear program with an integer bidirectional pairwise relaxation that halves load gaps along replica edges and nears the per-step optimum in a few passes. On decode routing from three open MoE families, scored as effective utilization relative to that optimum, the deployed static scheme reaches 66% to 72%, the GPU kernel 93%, and the on-die engine 99.5%, with the largest recovery over static placement at 37.3 percentage points.

In expert-parallel MoE serving, each layer finishes only when its most loaded GPU does, and routing shifts at every decode step. Relief replaces the per-step linear program with an integer bidirectional pairwise relaxation that halves load gaps along replica edges and nears the per-step optimum in a few passes. On decode routing from three open MoE families, scored as effective utilization relative to that optimum, the deployed static scheme reaches 66% to 72%, the GPU kernel 93%, and the on-die engine 99.5%, with the largest recovery over static placement at 37.3 percentage points.

Multimodal Rotary Position Embedding (MRoPE), widely used in vision-language models, assigns height and width coordinates to text tokens that have no inherent spatial structure, adding positional preferences to text-vision attention. The study separates intra-visual spatial encoding from cross-modal spatial effects, probing official pretrained checkpoints without training and running controlled training at 2B and 4B from identical initial parameters. Cross-modal spatial effects provide little extra benefit as spatial references and can even impair performance, while intra-visual spatial encoding remains useful for fine-grained grounding.

Multimodal Rotary Position Embedding (MRoPE), widely used in vision-language models, assigns height and width coordinates to text tokens that have no inherent spatial structure, adding positional preferences to text-vision attention. The study separates intra-visual spatial encoding from cross-modal spatial effects, probing official pretrained checkpoints without training and running controlled training at 2B and 4B from identical initial parameters. Cross-modal spatial effects provide little extra benefit as spatial references and can even impair performance, while intra-visual spatial encoding remains useful for fine-grained grounding.

Diffusion language models generate text in parallel through iterative denoising, but existing guidance methods build a weak model and pay an extra forward pass at every denoising step, doubling inference cost. GCG first shows these models lean on local context and underuse distant evidence during denoising, then amplifies the outputs of attention heads that carry global context directly in feature space, without a weak model. On LLaDA-8B, Dream-7B and LLaDA-1.5 it beats U-CFG and A-CFG across several benchmarks, while LLaDA-8B keeps the same FLOPs as the unguided baseline.

Diffusion language models generate text in parallel through iterative denoising, but existing guidance methods build a weak model and pay an extra forward pass at every denoising step, doubling inference cost. GCG first shows these models lean on local context and underuse distant evidence during denoising, then amplifies the outputs of attention heads that carry global context directly in feature space, without a weak model. On LLaDA-8B, Dream-7B and LLaDA-1.5 it beats U-CFG and A-CFG across several benchmarks, while LLaDA-8B keeps the same FLOPs as the unguided baseline.

Meeting transcription must output text for a requested speaker, but four-state activity conditioning collapses different interferer counts and hand-over histories into one target condition. Structured speaker conditioning encodes each speaker's activity track separately, combines it with session-level acoustic identity, and controls the acoustic encoder through condition-dependent low-rank cross-channel modulation. On Qwen3-ASR-0.6B with oracle diarization, the complete method uses 1.46M conditioning parameters and achieves a 6.23% mean relative cpER reduction over four-state diagonal conditioning across four meeting test sets.

Meeting transcription must output text for a requested speaker, but four-state activity conditioning collapses different interferer counts and hand-over histories into one target condition. Structured speaker conditioning encodes each speaker's activity track separately, combines it with session-level acoustic identity, and controls the acoustic encoder through condition-dependent low-rank cross-channel modulation. On Qwen3-ASR-0.6B with oracle diarization, the complete method uses 1.46M conditioning parameters and achieves a 6.23% mean relative cpER reduction over four-state diagonal conditioning across four meeting test sets.

Industrial search pipelines can return results on time and still show pages that fail the user's intent, while existing monitoring watches latency, availability and errors. WISE splits the diagnosis in two: it first judges whether a page has a quality problem using only user-facing multimodal evidence, then pulls internal pipeline evidence to attribute confirmed problems to supply, recall, relevance scoring, ranking or reranking. On WISE-Bench, 12,000 real search cases, Qwen3.5-35B-A3B rises from 35.25% to 75.20% end-to-end exact match after trajectory-supervised fine-tuning and AHPO.

Industrial search pipelines can return results on time and still show pages that fail the user's intent, while existing monitoring watches latency, availability and errors. WISE splits the diagnosis in two: it first judges whether a page has a quality problem using only user-facing multimodal evidence, then pulls internal pipeline evidence to attribute confirmed problems to supply, recall, relevance scoring, ranking or reranking. On WISE-Bench, 12,000 real search cases, Qwen3.5-35B-A3B rises from 35.25% to 75.20% end-to-end exact match after trajectory-supervised fine-tuning and AHPO.

Model merging usually trains every expert at the same LoRA rank, yet each domain has its own best rank. Across 36 experts on mathematics, instruction following and multilingual data at four ranks and three model scales, six merge methods were compared at uniform ranks and at each domain's own best rank: simple averaging and loss-utility component selection are unaffected and gain up to 1.8 pp of multi-domain accuracy, while magnitude-based conflict-resolution methods such as TIES and KnOTS are inconsistent and can lose up to 4 pp. The cause is that selecting components by size discards the instruction adapter, whose singular values are smallest, almost entirely, and IFEval falls by 16 to 25 pp.

Model merging usually trains every expert at the same LoRA rank, yet each domain has its own best rank. Across 36 experts on mathematics, instruction following and multilingual data at four ranks and three model scales, six merge methods were compared at uniform ranks and at each domain's own best rank: simple averaging and loss-utility component selection are unaffected and gain up to 1.8 pp of multi-domain accuracy, while magnitude-based conflict-resolution methods such as TIES and KnOTS are inconsistent and can lose up to 4 pp. The cause is that selecting components by size discards the instruction adapter, whose singular values are smallest, almost entirely, and IFEval falls by 16 to 25 pp.

CrossHair, a symbolic execution tool, barely runs on real Python web applications because the code ships without contracts and its database calls cannot be executed symbolically. A pipeline pairing an AI coding agent with CrossHair automatically writes contracts for functions and synthesizes a symbolic model of the database, raising the share of executable functions from 4.5% to 81% across 11 open-source applications and 1,156,044 lines of code, and finding 221 bugs reproduced by tests. These bugs are mostly input-domain corner cases, and some are missed by direct inspection with the same model.

CrossHair, a symbolic execution tool, barely runs on real Python web applications because the code ships without contracts and its database calls cannot be executed symbolically. A pipeline pairing an AI coding agent with CrossHair automatically writes contracts for functions and synthesizes a symbolic model of the database, raising the share of executable functions from 4.5% to 81% across 11 open-source applications and 1,156,044 lines of code, and finding 221 bugs reproduced by tests. These bugs are mostly input-domain corner cases, and some are missed by direct inspection with the same model.

Parallel test-time scaling for large language models normally generates every reasoning path to completion before internal confidence can score it, so compute on low-quality paths is already spent. PreG instead generates short prefixes in parallel, ranks them by internal confidence, and completes only the most promising candidates before aggregating as before. On Qwen3-8B and Llama-Nemotron-4B across math competition sets and GPQA-Diamond, it reaches the accuracy of the original method at a 1000k-token budget with fewer tokens, saving tokens in 54 of 60 configurations and up to 80%.

Parallel test-time scaling for large language models normally generates every reasoning path to completion before internal confidence can score it, so compute on low-quality paths is already spent. PreG instead generates short prefixes in parallel, ranks them by internal confidence, and completes only the most promising candidates before aggregating as before. On Qwen3-8B and Llama-Nemotron-4B across math competition sets and GPQA-Diamond, it reaches the accuracy of the original method at a 1000k-token budget with fewer tokens, saving tokens in 54 of 60 configurations and up to 80%.

Fixed transforms such as the discrete Fourier transform and discrete cosine transform are widely used in machine learning to extract features, but choosing among them usually requires knowing the dataset's properties, and the approach weakens when that knowledge is missing. The Adaptive Interpolating Transform (AIT) turns the transform itself into learnable parameters, learning data-driven mappings tailored to the dataset and task. On ImageNet-2012 and the General Language Understanding Evaluation tasks, AIT-enhanced models outperform fixed-transform baselines under both from-scratch and fine-tuning workflows, adding only nine parameters to vision models and three per encoder layer to language models.

Fixed transforms such as the discrete Fourier transform and discrete cosine transform are widely used in machine learning to extract features, but choosing among them usually requires knowing the dataset's properties, and the approach weakens when that knowledge is missing. The Adaptive Interpolating Transform (AIT) turns the transform itself into learnable parameters, learning data-driven mappings tailored to the dataset and task. On ImageNet-2012 and the General Language Understanding Evaluation tasks, AIT-enhanced models outperform fixed-transform baselines under both from-scratch and fine-tuning workflows, adding only nine parameters to vision models and three per encoder layer to language models.