Qualcomm (United States)

When a JEPA-style world model is regularized only through its embedding distribution, the encoder can treat the fixed background of each episode as its main content and suppress the state changes produced by robot-object interaction, a failure the authors call static collapse. The new method contrasts the predicted latent transition with transitions to other observations from the same episode, and uses optical-flow similarity as soft targets so candidates with similar motion receive similar supervision. Planning success rises from 52% to 78% over LeWM on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while four other visual-control benchmarks stay comparable.

When a JEPA-style world model is regularized only through its embedding distribution, the encoder can treat the fixed background of each episode as its main content and suppress the state changes produced by robot-object interaction, a failure the authors call static collapse. The new method contrasts the predicted latent transition with transitions to other observations from the same episode, and uses optical-flow similarity as soft targets so candidates with similar motion receive similar supervision. Planning success rises from 52% to 78% over LeWM on OGBench-Cube with randomized backgrounds and from 14% to 54% on LIBERO-Object, while four other visual-control benchmarks stay comparable.

Which target-model hidden layers a speculative-decoding draft model should see can now be chosen by information content and redundancy instead of a fixed positional rule; on Qwen3-4B-Instruct the selected three-layer set averages about 0.085 more accepted tokens than the EAGLE3 default.

Which target-model hidden layers a speculative-decoding draft model should see can now be chosen by information content and redundancy instead of a fixed positional rule; on Qwen3-4B-Instruct the selected three-layer set averages about 0.085 more accepted tokens than the EAGLE3 default.

Injecting random two-bit weight faults into agent executions turns model-level corruption into system-level outcomes: agents recover from malformed tool calls and still finish tasks, yet faulted runs raise mean output tokens by 38.0%, and some faults shift security and alignment behavior.

Injecting random two-bit weight faults into agent executions turns model-level corruption into system-level outcomes: agents recover from malformed tool calls and still finish tasks, yet faulted runs raise mean output tokens by 38.0%, and some faults shift security and alignment behavior.

The work introduces RFChipAgent, a superagent-orchestrated multi-agentic AI flow combining per-document FAISS-indexed multimodal RAG, a physics-aware topology agent, automated schematic and testbench generation, a TPE-plus-CMA-ES simulator-in-the-loop sizing optimizer, and a trust-scored simulation database; validated end-to-end on a GF22FDSOI 60 GHz wideband LNA, Trial #174 meets every specification, with the campaign completing in about 2 hours at an estimated cost of $156.20.

The work introduces RFChipAgent, a superagent-orchestrated multi-agentic AI flow combining per-document FAISS-indexed multimodal RAG, a physics-aware topology agent, automated schematic and testbench generation, a TPE-plus-CMA-ES simulator-in-the-loop sizing optimizer, and a trust-scored simulation database; validated end-to-end on a GF22FDSOI 60 GHz wideband LNA, Trial #174 meets every specification, with the campaign completing in about 2 hours at an estimated cost of $156.20.

The authors introduce LLoCoT, which replaces left-to-right latent generation with a few iterative refinement passes of a shared transformer over a compact latent workspace, then samples latent tokens in parallel from a probabilistic head to condition an autoregressive decoder; on HumanEval and MBPP it matches the accuracy of the explicit-CoT baseline Reasoning SFT and outperforms the base model, answer-only SFT and NF-CoT, while reducing time to the first answer token by about 36x, reasoning-phase latency by about 42x, and raising end-to-end throughput by 9.2%.

The authors introduce LLoCoT, which replaces left-to-right latent generation with a few iterative refinement passes of a shared transformer over a compact latent workspace, then samples latent tokens in parallel from a probabilistic head to condition an autoregressive decoder; on HumanEval and MBPP it matches the accuracy of the explicit-CoT baseline Reasoning SFT and outperforms the base model, answer-only SFT and NF-CoT, while reducing time to the first answer token by about 36x, reasoning-phase latency by about 42x, and raising end-to-end throughput by 9.2%.

MLCommons Jailbreak Benchmark v1.0 introduces an end-to-end methodology that evaluates eight open-weight large language models with paired baseline and adversarial conditions using 264 seed prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy, judging responses with the AILuminate Assessment Standard v1.4 and measuring robustness through the Resilience Gap; the unsafe-response rate rose from 11.08% at baseline to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57%, with accessible systems showing a larger mean gap and attack effectiveness varying substantially across attack categories and hazards.

MLCommons Jailbreak Benchmark v1.0 introduces an end-to-end methodology that evaluates eight open-weight large language models with paired baseline and adversarial conditions using 264 seed prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy, judging responses with the AILuminate Assessment Standard v1.4 and measuring robustness through the Resilience Gap; the unsafe-response rate rose from 11.08% at baseline to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57%, with accessible systems showing a larger mean gap and attack effectiveness varying substantially across attack categories and hazards.

The work proposes DyRA, an input-adaptive method that dynamically approximates and corrects the output residual error introduced by structured weight approximations (such as low-rank factorizations) during inference by directly optimizing low-rank factors of the output, yielding a more faithful approximation of full matrix multiplication under the same computational budget; across vision, speech, and language models, DyRA consistently improves the accuracy-efficiency trade-off over structured weight approximations alone, and notably achieves a 1.5x end-to-end GPU speedup for DINOv3 while reducing accuracy degradation by more than 3x.

The work proposes DyRA, an input-adaptive method that dynamically approximates and corrects the output residual error introduced by structured weight approximations (such as low-rank factorizations) during inference by directly optimizing low-rank factors of the output, yielding a more faithful approximation of full matrix multiplication under the same computational budget; across vision, speech, and language models, DyRA consistently improves the accuracy-efficiency trade-off over structured weight approximations alone, and notably achieves a 1.5x end-to-end GPU speedup for DINOv3 while reducing accuracy degradation by more than 3x.