MEMENTO: Teaching LLMs to Manage Their Own Context
Paper • 2604.09852 • Published • 1
Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted a paper about 8 hours ago
MEMENTO: Teaching LLMs to Manage Their Own Context upvoted a paper about 17 hours ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability upvoted a paper about 17 hours ago
SkillClaw: Let Skills Evolve Collectively with Agentic EvolverOrganizations
None yet
upvoted a paper about 8 hours ago
upvoted 5
papers about 17 hours ago
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 317
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 280
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 • 184
MolmoWeb: Open Visual Web Agent and Open Data for the Open Web
Paper • 2604.08516 • Published • 42
upvoted 14
papers about 20 hours ago
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Paper • 2604.02097 • Published • 32
LongCat-Next: Lexicalizing Modalities as Discrete Tokens
Paper • 2603.27538 • Published • 144
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward
Paper • 2603.26599 • Published • 64
EgoSim: Egocentric World Simulator for Embodied Interaction Generation
Paper • 2604.01001 • Published • 38
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 156
Brevity Constraints Reverse Performance Hierarchies in Language Models
Paper • 2604.00025 • Published • 23
The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning
Paper • 2603.29025 • Published • 13
Reasoning Shift: How Context Silently Shortens LLM Reasoning
Paper • 2604.01161 • Published • 32
Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants
Paper • 2604.00842 • Published • 14
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
Paper • 2603.28407 • Published • 69
Terminal Agents Suffice for Enterprise Automation
Paper • 2604.00073 • Published • 96
Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Paper • 2603.28376 • Published • 23
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Paper • 2604.02029 • Published • 142
A Survey of On-Policy Distillation for Large Language Models
Paper • 2604.00626 • Published • 11