BadWAM: When World-Action Models Dream Right but Act Wrong
Paper • 2607.15207 • Published • 53
Pedro Fernández
PedroFernandezzzz
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
BadWAM: When World-Action Models Dream Right but Act Wrong upvoted a paper 1 day ago
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration upvoted a paper 1 day ago
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement LearningOrganizations
None yet
upvoted 8
papers 1 day ago
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
Paper • 2607.15257 • Published • 69
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 97
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Paper • 2607.14935 • Published • 167
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 195
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
Paper • 2607.01774 • Published • 36
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
Paper • 2607.16617 • Published • 123
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Paper • 2607.19191 • Published • 200