Wuhan University

Super-resolution imaging flow cytometry (SR-IFC) brings structured-illumination microscopy into a continuous microfluidic stream: each cell yields only three phase-shifted frames, physical modulation sharpens the flow axis, and a network trained solely on the imaged sample's own data infers the missing transverse detail. On 100 nm fluorescent beads, SR-IFC reached about 118 nm along the flow axis and 110 nm across it, versus 222 to 227 nm for wide-field imaging of the same beads; with a 2048 × 320 pixel readout, the theoretical throughput ceiling is about 720 cells per second.

Super-resolution imaging flow cytometry (SR-IFC) brings structured-illumination microscopy into a continuous microfluidic stream: each cell yields only three phase-shifted frames, physical modulation sharpens the flow axis, and a network trained solely on the imaged sample's own data infers the missing transverse detail. On 100 nm fluorescent beads, SR-IFC reached about 118 nm along the flow axis and 110 nm across it, versus 222 to 227 nm for wide-field imaging of the same beads; with a 2048 × 320 pixel readout, the theoretical throughput ceiling is about 720 cells per second.

Locating RNA inosine sites has long relied on A-to-G base transitions in sequencing, which are hard to separate from DNA mutations and sequencing errors. REX-seq couples EndoV cleavage at inosines with XRN-1 degradation of fragments bearing 5′ phosphate ends, yielding cleavage signatures while preserving gene-expression quantification; in HEK293T cells it identified 590,249 high-confidence inosine sites, 84,645 of them not previously reported. Trained on these sites, InoDREAM reached an AUROC of 0.965 and average precision of 0.964 on a held-out test set, against 0.921 and 0.890 for EditPredict.

Locating RNA inosine sites has long relied on A-to-G base transitions in sequencing, which are hard to separate from DNA mutations and sequencing errors. REX-seq couples EndoV cleavage at inosines with XRN-1 degradation of fragments bearing 5′ phosphate ends, yielding cleavage signatures while preserving gene-expression quantification; in HEK293T cells it identified 590,249 high-confidence inosine sites, 84,645 of them not previously reported. Trained on these sites, InoDREAM reached an AUROC of 0.965 and average precision of 0.964 on a held-out test set, against 0.921 and 0.890 for EditPredict.

Medical imaging foundation models have traded generality against pixel-level precision, and most return a label without evidence. EVLF-FM feeds both disease-level and pixel-level visual features into a language model, first with supervised fine-tuning and then with reinforcement learning on verifiable rewards, spanning six specialties and 10 imaging modalities. On internal diagnostic validation it reached the highest mean accuracy among evaluated models, 0.895, and averaged 0.842 Acc@0.5 for medical visual grounding across nine modalities.

Medical imaging foundation models have traded generality against pixel-level precision, and most return a label without evidence. EVLF-FM feeds both disease-level and pixel-level visual features into a language model, first with supervised fine-tuning and then with reinforcement learning on verifiable rewards, spanning six specialties and 10 imaging modalities. On internal diagnostic validation it reached the highest mean accuracy among evaluated models, 0.895, and averaged 0.842 Acc@0.5 for medical visual grounding across nine modalities.

A two-dimensional grain-growth simulation hands area evolution to the von Neumann–Mullins law and microstructure reconstruction to a graph neural network, reaching the same coarsening stage on five initial microstructures in 38.43 s on average versus 5,247.01 s for phase-field.

A two-dimensional grain-growth simulation hands area evolution to the von Neumann–Mullins law and microstructure reconstruction to a graph neural network, reaching the same coarsening stage on five initial microstructures in 38.43 s on average versus 5,247.01 s for phase-field.

The work reformulates LLM-agent jailbreaking probabilistically: it shows that the gradient of the log expected harmfulness with respect to the input equals the expected log-likelihood gradient under a harmfulness-reweighted output distribution, unifying expected-harmfulness maximization with target-likelihood optimization; building on this, OPUR constructs surrogate targets from the model's own stochastic rollouts to guide adversarial suffix optimization, achieving higher targeted attack success rates on AgentHarm, InjecAgent, and WebShop.

The work reformulates LLM-agent jailbreaking probabilistically: it shows that the gradient of the log expected harmfulness with respect to the input equals the expected log-likelihood gradient under a harmfulness-reweighted output distribution, unifying expected-harmfulness maximization with target-likelihood optimization; building on this, OPUR constructs surrogate targets from the model's own stochastic rollouts to guide adversarial suffix optimization, achieving higher targeted attack success rates on AgentHarm, InjecAgent, and WebShop.

The authors propose LD-GTransNet: building on the multi-layer GTransNet approach, it adds a lift-and-decoupling strategy with preset hidden-layer neuron parameters and separate subnetworks for physical coordinates and an added auxiliary variable, giving a unified global approximation of piecewise smooth solutions without explicit domain decomposition and reducing the formulation to a linear least-squares problem that removes nonlinear training; numerical experiments on 2D and 3D benchmark interface problems show better accuracy and efficiency than existing neural-network and traditional numerical methods, especially for high-contrast coefficients and complex interface geometries.

The authors propose LD-GTransNet: building on the multi-layer GTransNet approach, it adds a lift-and-decoupling strategy with preset hidden-layer neuron parameters and separate subnetworks for physical coordinates and an added auxiliary variable, giving a unified global approximation of piecewise smooth solutions without explicit domain decomposition and reducing the formulation to a linear least-squares problem that removes nonlinear training; numerical experiments on 2D and 3D benchmark interface problems show better accuracy and efficiency than existing neural-network and traditional numerical methods, especially for high-contrast coefficients and complex interface geometries.

The authors introduce AECG, a multi-agent memory governance framework that combines scope preservation, asymmetric evidence admission, dual-timescale reliability estimation, and downstream-exposure-aware budgeted review to turn memory from static storage into a reliability-governance loop; across three frameworks (AutoGen, MacNet, AgentNet) and four benchmarks (PDDL, FEVER, ScienceWorld, MBPP-Plus), AECG achieves the best score in 11 of 12 settings, improving over the strongest memory baseline by up to 10.23 percentage points, while removing scope preservation reduces accuracy by up to 16.89 points.

The authors introduce AECG, a multi-agent memory governance framework that combines scope preservation, asymmetric evidence admission, dual-timescale reliability estimation, and downstream-exposure-aware budgeted review to turn memory from static storage into a reliability-governance loop; across three frameworks (AutoGen, MacNet, AgentNet) and four benchmarks (PDDL, FEVER, ScienceWorld, MBPP-Plus), AECG achieves the best score in 11 of 12 settings, improving over the strongest memory baseline by up to 10.23 percentage points, while removing scope preservation reduces accuracy by up to 16.89 points.

The work proposes GlitchPatch, an external framework that repairs glitch tokens without accessing model internals by optimizing input tokenization: offline, Behavioral Path Optimization (BPO) searches for the behaviorally optimal equivalent token sequence for each glitch token and compiles validated replacements into a rule table; online, only the IDs of matched glitch tokens in the canonical token sequence are substituted. Across ten models spanning six tokenizer families, it achieves an 85.10% mean fix rate, 14.37 percentage points above the strongest baseline, reduces the mean glitch rate from 14.88% to 2.27%, attains 0.00% regression in full-vocabulary evaluation, and keeps the mean online latency increase below 0.1%.

The work proposes GlitchPatch, an external framework that repairs glitch tokens without accessing model internals by optimizing input tokenization: offline, Behavioral Path Optimization (BPO) searches for the behaviorally optimal equivalent token sequence for each glitch token and compiles validated replacements into a rule table; online, only the IDs of matched glitch tokens in the canonical token sequence are substituted. Across ten models spanning six tokenizer families, it achieves an 85.10% mean fix rate, 14.37 percentage points above the strongest baseline, reduces the mean glitch rate from 14.88% to 2.27%, attains 0.00% regression in full-vocabulary evaluation, and keeps the mean online latency increase below 0.1%.

Coding agents often fill in underspecified requirements with their own assumptions, producing code that looks correct but behaves in ways the user never intended, and fixing that later grows costly. CONTRA splits clarification into broad question generation followed by semantic filtering and execution-based qualification, keeping only questions whose two plausible answers yield stable behavioral differences, then uses interaction history to ask or stop. On ClarifyCodeBench it reaches the highest F1 with all four coding agents, 13.88 percentage points above the best baseline macro-average.

Coding agents often fill in underspecified requirements with their own assumptions, producing code that looks correct but behaves in ways the user never intended, and fixing that later grows costly. CONTRA splits clarification into broad question generation followed by semantic filtering and execution-based qualification, keeping only questions whose two plausible answers yield stable behavioral differences, then uses interaction history to ask or stop. On ClarifyCodeBench it reaches the highest F1 with all four coding agents, 13.88 percentage points above the best baseline macro-average.

The work introduces Unite-Audio, which jointly learns continuous audio representations and latent flow matching for text-to-audio generation; by coupling reconstruction with self-supervised generative prediction it lets the generative objective directly shape the latent space, and it applies Flow-GRPO post-training to improve text-conditioned generation; experiments show competitive text-to-audio performance with a compact latent flow model, and ablation studies confirm the benefit of jointly learning the audio representation and the generative model.

The work introduces Unite-Audio, which jointly learns continuous audio representations and latent flow matching for text-to-audio generation; by coupling reconstruction with self-supervised generative prediction it lets the generative objective directly shape the latent space, and it applies Flow-GRPO post-training to improve text-conditioned generation; experiments show competitive text-to-audio performance with a compact latent flow model, and ablation studies confirm the benefit of jointly learning the audio representation and the generative model.