Daily Paper Cast
2,319 episodes — Page 3 of 47
TTPO: Test-Time Policy Optimization
Aug 28, 202620 min
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
Aug 28, 202620 min
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
Aug 28, 202620 min
UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Aug 28, 202622 min
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
Aug 28, 202619 min
GameWAM: A World Action Model for Video Games
Aug 28, 202622 min
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
Aug 28, 202621 min
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
Aug 27, 202619 min
FrontierChallenge: Evaluating Scientific Workflow Completion
Aug 27, 202624 min
VGI-Bench: Probing Visual Intelligence in Video Generation Models
Aug 27, 202618 min
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation
Aug 27, 202619 min
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Aug 27, 202620 min
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Aug 27, 202621 min
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity
Aug 26, 202619 min
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Aug 25, 202618 min
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
Aug 19, 202618 min
Agentic Transaction: Towards ACID-Compliant Agent Systems
Aug 19, 202620 min
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination
Aug 18, 202620 min
Self-Supervised Visual On-Policy Distillation
Aug 18, 202621 min
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Aug 18, 202622 min
Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning
Aug 18, 202625 min
Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence
Aug 18, 202621 min
Marionette: Predicting World States, Rendering Geometry, Painting Appearance
Aug 18, 202620 min
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
Aug 18, 202617 min
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
Aug 15, 202619 min
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
Aug 15, 202622 min
DarwinX: Evolving Agent Harnesses Through Natural Selection
Aug 15, 202620 min
Intern-S2-Preview: Scientific Agentic Foundation Model
Aug 15, 202623 min
How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review
Aug 15, 202620 min
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
Aug 15, 202621 min
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Aug 15, 202622 min
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
Aug 15, 202620 min
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
Aug 14, 202621 min
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Aug 14, 202621 min
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Aug 14, 202622 min
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Aug 14, 202622 min
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Aug 14, 202618 min
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
Aug 14, 202623 min
StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization
Aug 14, 202619 min
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI
Aug 13, 202622 min
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Aug 13, 202619 min
Beyond Pixels: From Video Priors to 4D Worlds
Aug 13, 202622 min
Articulated Object Reconstruction from Rest-State Observation
Aug 13, 202620 min
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss
Aug 13, 202619 min
Mendel G\"odel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
Aug 13, 202621 min
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Aug 12, 202621 min
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Aug 12, 202622 min
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Aug 12, 202619 min
On-Policy Self-Distillation without Any Supervision
Aug 12, 202620 min
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
Aug 12, 202620 min