Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

DeepSeek-OCR: Contexts Optical Compression

Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

AI for Service: Proactive Assistance with AI Glasses

WithAnyone: Towards Controllable and ID Consistent Image Generation

Agentic Entropy-Balanced Policy Optimization

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Predicting sequence-specific amplification efficiency in multi-template PCR with deep learning

The Genome Analysis Toolkit: A MapReduce framework for analyzing next-generation DNA sequencing data

LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search

Scaling Large Language Models for Next-Generation Single-Cell Analysis

A Survey of Vibe Coding with Large Language Models

Detect Anything via Next Point Prediction

Scaling Language-Centric Omnimodal Representation Learning

DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Asking Clarifying Questions for Preference Elicitation With Large Language Models

CTRL-Rec: Controlling Recommender Systems With Natural Language

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning

DeepSeek-OCR: Contexts Optical Compression

Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

Elucidated Rolling Diffusion Models for Probabilistic Weather Forecasting

ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

AI for Service: Proactive Assistance with AI Glasses

WithAnyone: Towards Controllable and ID Consistent Image Generation

Agentic Entropy-Balanced Policy Optimization

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA

Predicting sequence-specific amplification efficiency in multi-template PCR with deep learning

The Genome Analysis Toolkit: A MapReduce framework for analyzing next-generation DNA sequencing data

LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale

DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search

Scaling Large Language Models for Next-Generation Single-Cell Analysis

A Survey of Vibe Coding with Large Language Models

Detect Anything via Next Point Prediction

Scaling Language-Centric Omnimodal Representation Learning

DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Asking Clarifying Questions for Preference Elicitation With Large Language Models

CTRL-Rec: Controlling Recommender Systems With Natural Language