RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation

SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning

All is Not Lost: LLM Recovery without Checkpoints

Sundial: A Family of Highly Capable Time Series Foundation Models

ADRD: LLM-Driven Autonomous Driving Based on Rule-based Decision Systems

Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction

Show-o2: Improved Native Unified Multimodal Models

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models

EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

s1: Simple test-time scaling

Search-o1: Agentic Search-Enhanced Large Reasoning Models

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

GPT-4o System Card

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Aria: An Open Multimodal Native Mixture-of-Experts Model

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

VGGT: Visual Geometry Grounded Transformer

Multi-Turn Code Generation Through Single-Step Rewards

Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability

Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence

Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation

BUT System for the MLC-SLM Challenge

GenRecal: Generation after Recalibration from Large to Small Vision-Language Models

ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs

Sekai: A Video Dataset towards World Exploration

Data-driven material screening of secondary and natural cementitious precursors

RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation

SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning

All is Not Lost: LLM Recovery without Checkpoints

Sundial: A Family of Highly Capable Time Series Foundation Models

ADRD: LLM-Driven Autonomous Driving Based on Rule-based Decision Systems

Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction

Show-o2: Improved Native Unified Multimodal Models

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Raptor: Scalable Train-Free Embeddings for 3D Medical Volumes Leveraging Pretrained 2D Foundation Models

EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection

s1: Simple test-time scaling

Search-o1: Agentic Search-Enhanced Large Reasoning Models

LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

GPT-4o System Card

SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree

Aria: An Open Multimodal Native Mixture-of-Experts Model

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

VGGT: Visual Geometry Grounded Transformer

Multi-Turn Code Generation Through Single-Step Rewards

Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability

Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence

Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation

BUT System for the MLC-SLM Challenge

GenRecal: Generation after Recalibration from Large to Small Vision-Language Models

ProtoReasoning: Prototypes as the Foundation for Generalizable Reasoning in LLMs

Sekai: A Video Dataset towards World Exploration

Data-driven material screening of secondary and natural cementitious precursors