We have 5 of 13 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.
Libra is presented, which operationalizes the law of large numbers (LLN) as a scaling principle for load balancing: the attention-balancing pool need not grow with the DP degree.
Across reasoning, long-context understanding, and agentic tasks, SAS consistently outperforms trainable sparse attention baselines across attention budgets, with especially large gains under tight budgets, demonstrating more effective context ranking for downstream tasks.
Adaptive Log-Space (AL) quantization for non-negative states is introduced and its results make state topology and update semantics first-class design constraints for optimizer quantization.
Hierarchical Landmark Sparse Attention is proposed, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling (LM) loss, enabling long-context LLMs that are both more efficient and more effective on general long-context tasks than their full-attention counterparts.
This work proposes COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations, and evaluates on high-signal dynamic scenarios where historical context is most critical for behavior correctness, and accordingly design behavioral metrics.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
