MARS: Enabling Autoregressive Models Multi-Token Generation
Paper • 2604.07023 • Published • 29
Basil Cheer
basilcheer
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
MARS: Enabling Autoregressive Models Multi-Token Generation liked a model 3 days ago
zai-org/GLM-5.1Organizations
None yet
upvoted a paper 2 days ago
upvoted a paper 3 days ago
liked a
model 3 days ago
upvoted 3
papers 3 days ago
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Paper • 2604.05015 • Published • 224
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
Paper • 2604.01609 • Published • 10
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Paper • 2604.05404 • Published • 39
upvoted a changelog 4 days ago
Hugging Face Changelog
Agent Traces on the Hub
• 91
upvoted a paper 4 days ago
liked a
Space 4 days ago
upvoted 7
papers 4 days ago
LightThinker++: From Reasoning Compression to Memory Management
Paper • 2604.03679 • Published • 30
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 99
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Paper • 2604.04771 • Published • 112
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Paper • 2604.04707 • Published • 197
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 26
Self-Distilled RLVR
Paper • 2604.03128 • Published • 153
Test-Time Scaling Makes Overtraining Compute-Optimal
Paper • 2604.01411 • Published • 25
liked a
model 6 days ago
upvoted a paper 8 days ago
liked 2
models 8 days ago
