Daily Paper Cast
2,319 episodes — Page 2 of 47
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Sep 15, 202620 min
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Sep 15, 202620 min
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
Sep 15, 202621 min
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
Sep 15, 202622 min
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Sep 15, 202622 min
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction
Sep 11, 202624 min
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Sep 11, 202622 min
EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents
Sep 11, 202620 min
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
Sep 11, 202622 min
Show-Harness: Just a VLM Agent Can Play Robots
Sep 10, 202621 min
Programmable World Model
Sep 10, 202619 min
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data
Sep 10, 202621 min
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Sep 9, 202619 min
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
Sep 9, 202621 min
Omni Interaction Agent Technical Report
Sep 9, 202622 min
DriveZero: End-to-End Driving Beyond Human Demonstrations
Sep 9, 202622 min
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
Sep 9, 202620 min
Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout
Sep 9, 202620 min
AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing
Sep 9, 202619 min
Miles v0.1: Production-Level Post-Training
Sep 9, 202620 min
SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution
Sep 9, 202618 min
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Sep 4, 202622 min
LatentPress: Context Compression Beyond Text and Vision
Sep 4, 202620 min
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
Sep 4, 202620 min
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
Sep 4, 202620 min
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
Sep 4, 202622 min
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
Sep 4, 202622 min
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Sep 4, 202622 min
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Sep 3, 202621 min
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Sep 3, 202620 min
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
Sep 3, 202621 min
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
Sep 3, 202620 min
Language Models Can Control Their Own Attention
Sep 3, 202620 min
On the Design Fundamentals of Pixel Text Representation Learning
Sep 3, 202619 min
StudentSim: Training LLM-based Student Simulators
Sep 2, 202620 min
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Sep 2, 202621 min
UI-Venus-2 Technical Report
Sep 2, 202623 min
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Sep 2, 202621 min
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
Sep 2, 202620 min
H3-World: Turning Language Understanding into World Control
Sep 2, 202621 min
Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering
Sep 2, 202619 min
DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution
Sep 1, 202625 min
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Sep 1, 202620 min
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Sep 1, 202622 min
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
Sep 1, 202622 min
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
Sep 1, 202622 min
Normalized Low-Rank Adaptation
Sep 1, 202619 min
CogEvol: Towards Efficient and Reliable Learning Environment Generation
Sep 1, 202618 min
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Aug 28, 202620 min
PAWBench: How Far Are We from Probabilistically Aligned World Modeling?
Aug 28, 202621 min