MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
Paper • 2603.23516 • Published • 46
Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper about 14 hours ago
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens upvoted a paper 1 day ago
Efficient Universal Perception EncoderOrganizations
None yet
upvoted a paper about 14 hours ago
upvoted 6
papers 1 day ago
Efficient Universal Perception Encoder
Paper • 2603.22387 • Published • 6
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Paper • 2604.04323 • Published • 28
Falcon Perception
Paper • 2603.27365 • Published • 14
Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation
Paper • 2604.02368 • Published • 7
Self-Distilled RLVR
Paper • 2604.03128 • Published • 143
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 326
upvoted 5
papers 2 days ago
Agentic Critical Training
Paper • 2603.08706 • Published • 14
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
Paper • 2603.11327 • Published • 9
ActionParty: Multi-Subject Action Binding in Generative Video Games
Paper • 2604.02330 • Published • 6
Therefore I am. I Think
Paper • 2604.01202 • Published • 30
Meta-Harness: End-to-End Optimization of Model Harnesses
Paper • 2603.28052 • Published • 16
upvoted 8
papers 3 days ago
VOID: Video Object and Interaction Deletion
Paper • 2604.02296 • Published • 47
FlashSampling: Fast and Memory-Efficient Exact Sampling
Paper • 2603.15854 • Published • 9
LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
Paper • 2603.10899 • Published • 7
EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
Paper • 2603.12252 • Published • 12
Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
Paper • 2603.06577 • Published • 48
Lost in Backpropagation: The LM Head is a Gradient Bottleneck
Paper • 2603.10145 • Published • 12
Exclusive Self Attention
Paper • 2603.09078 • Published • 3
Adaptive Loops and Memory in Transformers: Think Harder or Know More?
Paper • 2603.08391 • Published • 1