
Daily Paper Cast
2,516 episodes — Page 2 of 51
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements
Nov 3, 202622 min
Democratizing Robot-Use Agents: A Unified Harness with Open Models
Nov 3, 202622 min
NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
Nov 3, 202622 min
Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning
Nov 3, 202621 min
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
Nov 3, 202622 min
Intrinsic Distribution Matching
Oct 30, 202622 min
Your Benchmark Is an Empirical Measure Over Difficulty
Oct 30, 202621 min
Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
Oct 30, 202621 min
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
Oct 30, 202621 min
WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training
Oct 30, 202623 min
L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
Oct 30, 202622 min
A Broader Look into MLLM's Retrieval Heads
Oct 30, 202622 min
DTCA: Denoising Token Credit Assignment for Reinforcement Learning in Diffusion Language Models
Oct 29, 202621 min
Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes
Oct 29, 202620 min
Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
Oct 29, 202622 min
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
Oct 29, 202621 min
ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence
Oct 28, 202624 min
PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
Oct 28, 202622 min
Hy-Nomas: Towards Free-form Interactive World Generation
Oct 28, 202622 min
HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory
Oct 28, 202623 min
Rollback: Experience Backtracking in World Models for Policy Improvement
Oct 28, 202619 min
CodeCap-Bench: Can Code Serve as a Good Video Caption?
Oct 28, 202627 min
Memory Tax: Dissecting the Net Value of Agent Memory
Oct 28, 202620 min
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Oct 28, 202623 min
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Oct 28, 202620 min
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
Oct 27, 202622 min
StreamVibe: Proactive Video Agents for Evolving User Intent
Oct 27, 202621 min
Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
Oct 27, 202624 min
InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
Oct 27, 202622 min
DynaFlow: Learning Free-Form Multi-Agent Orchestration
Oct 27, 202619 min
WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control
Oct 27, 202622 min
Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion
Oct 27, 202620 min
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL
Oct 27, 202621 min
Deep Search in Real-World Web Environments
Oct 23, 202622 min
Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation
Oct 23, 202621 min
Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models
Oct 23, 202622 min
LaLa-World: Scaling Latent World Models with Natural Language Actions
Oct 23, 202620 min
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
Oct 23, 202621 min
Toward Recursive Self-Improvement in Physical AI
Oct 23, 202620 min
Cache Engineering for Agents
Oct 22, 202623 min
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
Oct 22, 202622 min
Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
Oct 22, 202620 min
PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis
Oct 22, 202622 min
Spectral-Spatial Interpretation
Oct 22, 202623 min
Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills
Oct 22, 202624 min
StreamEval: Evaluating Interactive Streaming Video Generation Models
Oct 22, 202621 min
Focused Omni-Modal GUI Agents
Oct 21, 202620 min
PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
Oct 21, 202621 min
S-Agent 2.0: Spatial Reasoning with a General Coding Agent
Oct 21, 202623 min
Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition
Oct 21, 202623 min