We have 17 of 63 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Medical question answering spans specialties and clinical operations that may benefit from different adaptation directions. We propose ARBOR, a parameter-efficient method that selects rank-one components from a shared low-rank basis for each question. An additive gate combines question representations, specialty tags,...
Scientific literature synthesis agents increasingly rely on proprietary online services, limiting reproducibility, privacy, and offline deployment. To address this challenge, we introduce SciLENS Scientific Localized Evidence Navigation and Synthesis), a fully local autonomous agent framework operating on a dual-tier i...
Causal Imprint is introduced, which learns future-relevant scene changes from training-only future supervision and provides predictive representations directly to the action expert without future-video rollout at inference.
Language models can over-condition on irrelevant preceding text: predictions already supported by local context may still change when distant, unrelated prefix tokens are perturbed. This interference is especially consequential in long, packed, or distractor-heavy contexts, where useful evidence and irrelevant spans co...
Adaptive Hierarchical Representation Alliance (AHRA), a hierarchical shared--private expert framework, is proposed, which consistently improves over strong baselines and remains robust under noisy and missing-modality settings.
Gradient-Aligned Reward (GAR), which operates in the policy's own gradient space: truncated backpropagation through the output projection layer extracts a compact gradient vector for each rollout, and cosine similarity with an expert-anchor gradient yields a dense, reasoning-aware reward with less than 9% wall-clock ov...
The findings reveal that predictive learning objectives impose strong regularities on representation geometry, suggesting a lightweight path to interoperability among decentralized vision systems.
CM2 is proposed, a multi-agent framework grounded in the cognitive pathway of human cultural interpretation that integrates multimodal perception, retrieval-augmented generation, networked reasoning, gated fusion, and reward-driven feedback.
GapSight is proposed, a framework for learning visual re-reading: a VLM first takes a global glance, then selectively returns to a free-form region when the question calls for local evidence, and Mechanism analyses show that the router rescues concrete wrong answers, adapts its action rate by task, and forms a favorabl...
ExACT, a supervision-allocation objective that assigns extra weight to long effective-context targets by inverse frequency within the long tail, supports a supervision-centric thesis: long-context adaptation depends on how strongly training supervises long-context predictions.
Juris Policy Optimization (JPO), a post-training framework for structured legal reasoning in Chinese criminal judgment prediction, is proposed and experiments show that JPO consistently improves both judgment prediction and reasoning quality over supervised fine-tuning and reinforcement learning baselines.
TrustEndo is introduced, a framework that addresses both problems of hallucination of plausible-yet-wrong claims, and the lack of statistical guarantees on output reliability through three modules that extends conformal prediction to multimodal outputs, providing coverage guarantees over detection predictions under exc...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
