Accelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime Pipelining Paper • 2611.26268 • Published 2 days ago • 17
UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models Paper • 2611.18668 • Published 26 days ago • 5
On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer Paper • 2611.06976 • Published 17 days ago • 16
Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities Paper • 2610.39301 • Published 23 days ago • 18
HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs Paper • 2610.26770 • Published Oct 19 • 33
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published Sep 17 • 209
Thinking in Video: Can Video Generators Really Reason About the Real World? Paper • 2607.17523 • Published Jul 20 • 1
PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity Paper • 2510.04080 • Published Feb 28 • 2
ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL Paper • 2608.28476 • Published Aug 28 • 31
Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge Paper • 2608.28478 • Published Aug 28 • 18
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI Paper • 2606.14502 • Published Jun 12 • 61
HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention Paper • 2603.28458 • Published Mar 30 • 41
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning Paper • 2603.16929 • Published Mar 14 • 12
Deep Tabular Research via Continual Experience-Driven Execution Paper • 2603.09151 • Published Mar 10 • 13
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion Paper • 2603.06577 • Published Mar 6 • 49