We have 7 of 74 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.
Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended temporal spans. Existing approaches broadly follow two paradigms: query-driven exploration, which is sensitive to localization errors, and query-independent memory cons...
Groupwise Reward Geometry Conditioning (GRGC) is proposed, a two-stage framework that improves advantage construction by shaping student-side reward groups during both critic training and policy optimization, and introduces negligible overhead over GAD.
Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without degrading pretrained skills remains challenging. We explore on-policy distillation (OPD) for WAMs and introduce WAM-OPD. WAM-OPD inherits the...
The Multi-Level Optimal Transport (MultiLevelOT) is introduced, a novel approach that advances the optimal transport for universal cross-tokenizer knowledge distillation and is robust to different student and teacher models across model families, architectures, and parameter sizes.
HIEVI-RAG is introduced, a hierarchical, evidence-driven multimodal RAG framework for closed-domain document understanding that significantly outperforms existing open-source baselines and exceeds the strongest reported baseline by an average of 8.05% in accuracy.
HierDoc, a hierarchical evidence-routing framework that formulates long-document evidence acquisition as two-stage set prediction from pages to regions, achieves state-of-the-art or competitive performance among open-weight systems, improving LongDocURL by 16.87% relative to the strongest reported open-weight baseline.
Experiments across various datasets indicate that the proposed method achieves superior reasoning accuracy without compromising, and even facilitating, the overall accuracy, and ablation studies show that the proposed mechanisms can provide flexible control interfaces for the tradeoff between the reasoning accuracy and...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
