Daily Paper Cast
1,976 episodes — Page 5 of 40
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
Apr 17, 202626 min
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Apr 17, 202624 min
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Apr 17, 202624 min
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
Apr 17, 202627 min
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
Apr 17, 202626 min
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
Apr 17, 202623 min
Exploration and Exploitation Errors Are Measurable for Language Model Agents
Apr 17, 202622 min
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
Apr 16, 202623 min
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Apr 16, 202625 min
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
Apr 16, 202621 min
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Apr 16, 202622 min
Toward Autonomous Long-Horizon Engineering for ML Research
Apr 16, 202624 min
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
Apr 16, 202621 min
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
Apr 15, 202624 min
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Apr 15, 202621 min
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
Apr 15, 202621 min
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Apr 15, 202621 min
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Apr 15, 202621 min
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
Apr 15, 202622 min
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Apr 15, 202623 min
CocoaBench: Evaluating Unified Digital Agents in the Wild
Apr 15, 202622 min
CodeTracer: Towards Traceable Agent States
Apr 15, 202623 min
WildDet3D: Scaling Promptable 3D Detection in the Wild
Apr 14, 202625 min
FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
Apr 14, 202621 min
EXAONE 4.5 Technical Report
Apr 14, 202623 min
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
Apr 14, 202622 min
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Apr 14, 202623 min
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Apr 11, 202624 min
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Apr 11, 202622 min
RAGEN-2: Reasoning Collapse in Agentic RL
Apr 10, 202625 min
MARS: Enabling Autoregressive Models Multi-Token Generation
Apr 10, 202623 min
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Apr 10, 202621 min
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
Apr 9, 202624 min
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Apr 9, 202622 min
Learning to Retrieve from Agent Trajectories
Apr 9, 202622 min
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Apr 9, 202624 min
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
Apr 9, 202623 min
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Apr 9, 202621 min
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement
Apr 9, 202622 min
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
Apr 9, 202624 min
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
Apr 9, 202625 min
Watch Before You Answer: Learning from Visually Grounded Post-Training
Apr 9, 202620 min
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Apr 8, 202623 min
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Apr 8, 202623 min
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
Apr 8, 202622 min
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Apr 8, 202621 min
Adam's Law: Textual Frequency Law on Large Language Models
Apr 8, 202622 min
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Apr 8, 202623 min
ClawArena: Benchmarking AI Agents in Evolving Information Environments
Apr 8, 202621 min
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
Apr 8, 202622 min