Daily Paper Cast
2,319 episodes — Page 1 of 47
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Sep 30, 202625 min
MaLiang-Harness: A Programmable Path to Image and Video Generation
Sep 30, 202623 min
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation
Sep 30, 202621 min
Omni-IO Skills: Harnessing Your Agent Omni-Native
Sep 30, 202622 min
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Sep 30, 202620 min
VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models
Sep 30, 202620 min
Think Before You Score: Thinking Reward Model for Visual Generation
Sep 30, 202622 min
In-Context Learning for Robots: Methods and Applications
Sep 30, 202621 min
Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Sep 30, 202621 min
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
Sep 30, 202622 min
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
Sep 29, 202621 min
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Sep 29, 202621 min
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
Sep 29, 202620 min
Post-Training Leaves Behavioral Shadows on Unrelated Decisions
Sep 29, 202619 min
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
Sep 29, 202622 min
Improving Test-Time Scaling with Adaptive Looped Transformers
Sep 29, 202622 min
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
Sep 29, 202618 min
EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks
Sep 29, 202624 min
CompoWorld: Compositional Environment Scaling for General Agents
Sep 29, 202622 min
Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue
Sep 29, 202618 min
Training Object Permanence in World Models
Sep 25, 202623 min
The Past Frames the Future: Memory for Autoregressive Video Generation
Sep 24, 202617 min
HappyWorld-Bench
Sep 24, 202624 min
RULER: Instance-aware Rubric Rewards for SVG Generation
Sep 23, 202621 min
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Sep 23, 202621 min
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts
Sep 23, 202620 min
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Sep 22, 202623 min
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory
Sep 22, 202620 min
GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
Sep 22, 202622 min
Transferring the Intelligence of VLMs to Robotic Control
Sep 22, 202621 min
VideoGen-Agent: Reinforcing Video Generation Agents
Sep 22, 202625 min
OmniEdu: Open Foundation Models for Learning and Teaching
Sep 22, 202624 min
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Sep 18, 202622 min
An Empirical Study of Harness Design for Coding Agents
Sep 18, 202623 min
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
Sep 18, 202623 min
JEPA-Anything: Learning Predictive Models across Different Worlds
Sep 18, 202619 min
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Sep 17, 202621 min
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
Sep 17, 202623 min
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
Sep 17, 202622 min
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Sep 17, 202620 min
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Sep 17, 202621 min
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention
Sep 17, 202623 min
Agora: Git as Shared Memory for Collective AutoResearch
Sep 17, 202621 min
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Sep 17, 202621 min
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control
Sep 17, 202621 min
A Zeroth-Order Paradigm for LLM Preference Alignment
Sep 17, 202620 min
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Sep 16, 202622 min
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Sep 16, 202621 min
StepAudio 3 Realtime Technical Report
Sep 16, 202622 min
Atria Dawn: The Dawn of Agentic Superintelligence
Sep 15, 202621 min