PLAY PODCASTS
Daily Paper Cast

Daily Paper Cast

2,516 episodes — Page 3 of 51

Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds

Oct 21, 202620 min

Learning the 4D World through Point Trajectory Forecasting

Oct 21, 202620 min

SolarRenderer: Few-Step Generative Reference Rendering

Oct 21, 202621 min

VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse

Oct 21, 202622 min

CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?

Oct 21, 202622 min

Learning from Fleet Experience: A Collective Learning Paradigm for Robots

Oct 20, 202619 min

ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation

Oct 20, 202624 min

Self-Evolving Coding Agents via Harness-Policy Optimization

Oct 20, 202624 min

MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion

Oct 20, 202621 min

CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents

Oct 20, 202623 min

EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience

Oct 20, 202621 min

OR-License: Evaluating LLM Agents as Real-World Operations Research Practitioners

Oct 20, 202620 min

Holi-World: Building Holistic World Intelligence from Human-Ego Experience

Oct 20, 202621 min

RoAR-VAE: Improving Latent Diffusability through Robust Prediction

Oct 20, 202621 min

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Oct 16, 202622 min

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Oct 16, 202619 min

Self-Evolving Agent Harness

Oct 16, 202622 min

Speculative Forcing for Efficient Autoregressive Video Generation

Oct 16, 202622 min

Learning Where to Split: Dynamic Band Splitting for Audio Source Separation

Oct 16, 202622 min

SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation

Oct 16, 202621 min

3DCodeVerse: Exploring 3D Worlds as Code

Oct 16, 202622 min

Orbia: Do Generated Videos Form a Consistent 3D World?

Oct 16, 202621 min

Mosaic: Multi-Session Agentic Reinforcement Learning

Oct 16, 202623 min

DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding

Oct 16, 202621 min

Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

Oct 15, 202623 min

Player-1: Learning to Play from Synthetic Experience

Oct 15, 202623 min

LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation

Oct 15, 202621 min

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

Oct 15, 202620 min

Cortex: Consolidating Context into Parametric Memory

Oct 15, 202622 min

ActionOPD: Distilling Decisions, Not Tokens

Oct 15, 202621 min

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

Oct 15, 202619 min

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Oct 15, 202619 min

LensErase: A Foundation Model for Erase Anything

Oct 15, 202622 min

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

Oct 15, 202625 min

Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes

Oct 14, 202622 min

Vela: User Behavior as Supervision Sparks LLM Intelligence

Oct 14, 202623 min

DoSA: Dots Sparse Attention

Oct 14, 202621 min

LeWAM: End-to-End World and Action Modeling with JEPAs

Oct 14, 202621 min

Jeva: System One Models from First Principles

Oct 14, 202622 min

TPPO: Tracking-Value PPO For Language Model Reasoning

Oct 14, 202621 min

VideoJev: System One Model for Video Understanding and Interaction

Oct 14, 202624 min

Harness^2: Recursive Agent Harnessing for an Open World

Oct 14, 202622 min

UltraBERT: Beyond the Limit of BERT Pre-Training

Oct 14, 202621 min

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Oct 14, 202621 min

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Oct 13, 202623 min

Scaling Agentic Data for Long-Horizon Terminal Intelligence

Oct 13, 202619 min

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

Oct 13, 202621 min

Thinking Inertia: LLMs Keep Thinking When Told Not To

Oct 13, 202623 min

Multi-Stream Attention Residuals

Oct 13, 202623 min

Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents

Oct 13, 202618 min