Daily Paper Cast
2,319 episodes — Page 7 of 47
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Jul 9, 202620 min
Vision as Unified Multimodal Generation
Jul 9, 202626 min
Gemma 4 Technical Report
Jul 9, 202623 min
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
Jul 8, 202620 min
UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning
Jul 8, 202621 min
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Jul 8, 202623 min
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
Jul 8, 202623 min
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Jul 8, 202627 min
MANCE: Manifold Aware Concept Erasure
Jul 8, 202622 min
GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation
Jul 8, 202625 min
Wan-Streamer v0.2: Higher Resolution, Same Latency
Jul 8, 202621 min
EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots
Jul 8, 202622 min
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Jul 7, 202621 min
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
Jul 7, 202622 min
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Jul 7, 202623 min
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Jul 7, 202620 min
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Jul 7, 202622 min
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Jul 4, 202624 min
AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents
Jul 4, 202623 min
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Jul 4, 202623 min
Morphing into Hybrid Attention Models
Jul 4, 202624 min
AgenticDataBench: A Comprehensive Benchmark for Data Agents
Jul 4, 202621 min
Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling
Jul 4, 202622 min
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
Jul 3, 202621 min
Orca: The World is in Your Mind
Jul 2, 202624 min
Dockerless: Environment-Free Program Verifier for Coding Agents
Jul 2, 202624 min
DOPD: Dual On-policy Distillation
Jul 2, 202625 min
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Jul 2, 202621 min
Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views
Jul 2, 202623 min
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Jul 2, 202626 min
Multi-Block Diffusion Language Models
Jul 2, 202623 min
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
Jul 1, 202624 min
LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing
Jul 1, 202623 min
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Jul 1, 202626 min
TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
Jul 1, 202622 min
Beyond IID: How General Are Tabular Foundation Models, Really?
Jul 1, 202622 min
Trimming the Long-Tail of Visual World Modeling Evaluation
Jul 1, 202625 min
AsyncOPD: How Stale Can On-Policy Distillation Be?
Jul 1, 202622 min
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning
Jul 1, 202620 min
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
Jul 1, 202622 min
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Jun 30, 202621 min
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots
Jun 30, 202623 min
Qwen-Image-2.0-RL Technical Report
Jun 30, 202627 min
DanceOPD: On-Policy Generative Field Distillation
Jun 28, 202625 min
In-Context World Modeling for Robotic Control
Jun 28, 202623 min
Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation
Jun 28, 202621 min
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
Jun 28, 202623 min
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Jun 28, 202622 min
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
Jun 28, 202625 min
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
Jun 28, 202620 min