…evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided…
…These graphs reveal multi-hop license obligations , train-evaluation coupling , discrepancies between released and training-time artifacts, and documentation inconsistencies that would otherwise be difficult to uncover. We release ModSleuth and the…
…Across three model families and multiple factual QA benchmarks, RL yields ~27% average relative gains, surpassing both training- and inference-time baselines alike. Mechanistically, RL primarily redistributes probability mass over existing knowledge…
…AI-generated summary Humanoid control systems have made significant progress in recent years, yet modeling fluent interaction-rich behavior between a robot, its surrounding environment, and task-relevant objects remains a fundamental…
…This calls for context learning , where LMs directly learn relevant knowledge from the given context. An intuitive solution is inference-time skill augmentation : extracting the rules and procedures from context into natural…
…A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs (2026) Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time (2026) Reducing Linguistic Hallucination in LM-Based Speech Enhancement via…
…MAAT scores adapter rank dimensions by forget-set activation/gradient relevance, prunes or negates only the most forget-associated subspace, and repairs retained behavior without merging into or modifying the frozen base…
…Through a closed-loop run--verify--reflect process , the framework jointly improves decomposition and execution over time via persistent, human-readable external memory , with self-evolving updates to each single-agent. During…
…I want to fintune ASR and LID at the same time. How to do it? · why do you need LID? Isn't that a different task? if your dataset is multilingual you…
…early layers form coarse guesses, intermediate layers refine reasoning-relevant semantics, and final layers can perturb these refined predictions toward generic or alignment-preferred tokens. We introduce Confident Decoding , a training-free…