Daily Papers of 2026-07-09
- Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning 85 upvotes, #1 of 2026-07-09
- Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence 62 upvotes, #2 of 2026-07-09
- Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation 55 upvotes, #3 of 2026-07-09
- Infinite Worlds with Versatile Interactions 42 upvotes, #4 of 2026-07-09
- Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning 23 upvotes, #5 of 2026-07-09
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies 14 upvotes, #6 of 2026-07-09
- WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence 14 upvotes, #6 of 2026-07-09
- Automating the Design of Embodied Agent Architectures 12 upvotes, #8 of 2026-07-09
- Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity 12 upvotes, #8 of 2026-07-09
- AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation 8 upvotes, #10 of 2026-07-09
- OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators 8 upvotes, #10 of 2026-07-09
- OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies 5 upvotes, #12 of 2026-07-09
- Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo 5 upvotes, #12 of 2026-07-09
- RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures 5 upvotes, #12 of 2026-07-09
- Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure 3 upvotes, #15 of 2026-07-09
- Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs 2 upvotes, #16 of 2026-07-09
- TESSERA v2: Scaling Pixel-wise Earth Foundation Models 2 upvotes, #16 of 2026-07-09
- Token-Based Dual-view Fusion and Adaptation of Large Vision Models for Breast Cancer Classification 2 upvotes, #16 of 2026-07-09
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.