SkillNet: Create, Evaluate, and Connect AI Skills

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

SURvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Heterogeneous Agent Collaborative Reinforcement Learning

Helios: Real Real-Time Long Video Generation Model

Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games

Speculative Speculative Decoding

Using Learning Progressions to Guide AI Feedback for Science Learning

HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals

Gravity Falls: A Comparative Analysis of Domain-Generation Algorithm (DGA) Detection Methods for Mobile Device Spearphishing

From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence

The Design Space of Tri-Modal Masked Diffusion Models

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

RubricBench: Aligning Model-Generated Rubrics with Human Standards

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

OpenAutoNLU: Open Source AutoML Library for NLU

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

Multi-agent cooperation through in-context co-player inference

ACTIONENGINE: From Reactive to Programmatic GUI Agents via State Machine Memory

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

Mode Seeking meets Mean Seeking for Fast Long Video Generation

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

Enhancing Spatial Understanding in Image Generation via Reward Modeling

SkillNet: Create, Evaluate, and Connect AI Skills

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

SURvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis

PanoWan: Lifting Diffusion Video Generation Models to 360° with Latitude/Longitude-aware Mechanisms

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Proact-VL: A Proactive VideoLLM for Real-Time AI Companions

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Heterogeneous Agent Collaborative Reinforcement Learning

Helios: Real Real-Time Long Video Generation Model

Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games

Speculative Speculative Decoding

Using Learning Progressions to Guide AI Feedback for Science Learning

HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations

Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals

Gravity Falls: A Comparative Analysis of Domain-Generation Algorithm (DGA) Detection Methods for Mobile Device Spearphishing

From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence

The Design Space of Tri-Modal Masked Diffusion Models

CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning

RubricBench: Aligning Model-Generated Rubrics with Human Standards

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

OpenAutoNLU: Open Source AutoML Library for NLU

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

From Scale to Speed: Adaptive Test-Time Scaling for Image Editing

Multi-agent cooperation through in-context co-player inference

ACTIONENGINE: From Reactive to Programmatic GUI Agents via State Machine Memory

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

Mode Seeking meets Mean Seeking for Fast Long Video Generation

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets

Enhancing Spatial Understanding in Image Generation via Reward Modeling