GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

ReCA: Integrated Acceleration for Real-Time and Efficient Cooperative Embodied Autonomous Agents

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos

TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning

GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models

Modeling protein-small molecule conformational ensembles with PLACER

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation

AI Assisted AR Assembly: Object Recognition and Computer Vision for Augmented Reality Assisted Assembly

Jailbreaking in the Haystack

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

Visual Spatial Tuning

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

DeepEyesV2: Toward Agentic Multimodal Model

Use of Continuous Glucose Monitoring with Machine Learning to Identify Metabolic Subphenotypes and Inform Precision Lifestyle Changes

Reusing Pre-Training Data at Test Time is a Compute Multiplier

NVIDIA Nemotron Nano V2 VL

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

Cambrian-S: Towards Spatial Supersensing in Video

Scaling Agent Learning via Experience Synthesis

V-Thinker: Interactive Thinking with Images

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Recent Developments in Amber Biomolecular Simulations

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers

Node-Based Editing for Multimodal Generation of Text, Audio, Image, and Video

DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

ReCA: Integrated Acceleration for Real-Time and Efficient Cooperative Embodied Autonomous Agents

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos

TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning

GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models

Modeling protein-small molecule conformational ensembles with PLACER

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

DiaMoE-TTS: A Unified IPA-Based Dialect TTS Framework with Mixture-of-Experts and Parameter-Efficient Zero-Shot Adaptation

AI Assisted AR Assembly: Object Recognition and Computer Vision for Augmented Reality Assisted Assembly

Jailbreaking in the Haystack

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

Visual Spatial Tuning

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains

DeepEyesV2: Toward Agentic Multimodal Model

Use of Continuous Glucose Monitoring with Machine Learning to Identify Metabolic Subphenotypes and Inform Precision Lifestyle Changes

Reusing Pre-Training Data at Test Time is a Compute Multiplier

NVIDIA Nemotron Nano V2 VL

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

Cambrian-S: Towards Spatial Supersensing in Video

Scaling Agent Learning via Experience Synthesis

V-Thinker: Interactive Thinking with Images

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Recent Developments in Amber Biomolecular Simulations

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers

Node-Based Editing for Multimodal Generation of Text, Audio, Image, and Video

DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration

Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning