Neural Garbage Collection: Learning to Forget while Learning to Reason
Paper • 2604.18002 • Published • 2
Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
Neural Garbage Collection: Learning to Forget while Learning to Reason upvoted a paper about 9 hours ago
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence upvoted a paper about 9 hours ago
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit FlipsOrganizations
None yet
upvoted a paper about 8 hours ago
upvoted 3
papers about 9 hours ago
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Paper • 2604.18292 • Published • 81
Maximal Brain Damage Without Data or Optimization: Disrupting Neural Networks via Sign-Bit Flips
Paper • 2502.07408 • Published • 58
When Can LLMs Learn to Reason with Weak Supervision?
Paper • 2604.18574 • Published • 25
upvoted an article about 10 hours ago
Article
DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models
•
34
upvoted 3
papers 2 days ago
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 375
Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers
Paper • 2604.07822 • Published • 1
Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter
Paper • 2604.15039 • Published • 2
upvoted 2
papers 6 days ago
upvoted 3
papers 8 days ago
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Paper • 2604.14268 • Published • 116
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Paper • 2604.14228 • Published • 25
Geometric Context Transformer for Streaming 3D Reconstruction
Paper • 2604.14141 • Published • 19
upvoted 7
papers 9 days ago
MEMENTO: Teaching LLMs to Manage Their Own Context
Paper • 2604.09852 • Published • 1
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 323
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 287
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Paper • 2604.05333 • Published • 22
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 187
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Paper • 2604.08516 • Published • 42
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Paper • 2604.02097 • Published • 32