Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
Paper • 2610.30926 • Published • 61
Evan Fabre
masimon644
AI & ML interests
Research on LLM agents and evaluation. Mostly focused on experiments.
Recent Activity
liked a model 5 days ago
microsoft/LLM2CLIP-Llama-3-8B-Instruct-CC-Finetuned liked a model 5 days ago
deepseek-ai/DeepSeek-V2-Lite liked a model 5 days ago
mistralai/Mistral-7B-Instruct-v0.2Organizations
None yet
upvoted 2
papers 9 days ago
upvoted 2
papers 11 days ago
upvoted a paper 12 days ago
upvoted 8
papers 13 days ago
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
Paper • 2606.24428 • Published • 17
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 140
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 80
Demystifying Agent Skills: Why They Work-Until They Don't
Paper • 2608.14036 • Published • 68
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey
Paper • 2607.21655 • Published • 87
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 100
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
Paper • 2608.16859 • Published • 91
ABot-Earth 0.5: Generative 3D Earth Model
Paper • 2606.09967 • Published • 184
upvoted 5
papers 15 days ago
DAPD: Dual-Anchored Policy Distillation
Paper • 2608.01735 • Published • 62
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning
Paper • 2609.03199 • Published • 14
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Paper • 2609.11977 • Published • 70
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Paper • 2609.08183 • Published • 89
Omni-IO Skills: Harnessing Your Agent Omni-Native
Paper • 2609.31847 • Published • 92
upvoted 2
papers 16 days ago