Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes.
논문·연구
16/17쪽MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of policies do not preserve and leverage episode-level information…
Hunyuan-A13B Technical Report
We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture.
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
AI research agents need reliable knowledge of how their experiments change outcomes.
All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation
Video is a rich representation of a physical event, capturing appearance, geometry, motion, and temporal evolution.
On the Diffusibility of High-Dimensional Latents
Representation Autoencoders (RAEs) enable diffusion models to operate in the feature spaces of pretrained visual encoders.
InternW0: A Foundational Physical World Model for Efficient Real-World Interactions
Physical intelligence requires more than predicting how the world may evolve: predictions must remain actionable as the world continues to change.
FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
Solutions based on large language models (LLMs) often rely on temperature sampling to improve accuracy and stability by aggregating multiple samples from the completion…