Articles de Recherche en IA Quotidiens

Knowledge Base Construction for Knowledge-Augmented Text-to-SQL

Reverse Preference Optimization for Complex Instruction Following

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Skywork Open Reasoner 1 Technical Report

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPO

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

SageAttention2++: A More Efficient Implementation of SageAttention2

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start

RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination

Fostering Video Reasoning via Next-Event Prediction

DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research

Hard Negative Mining for Domain-Specific Retrieval in Enterprise Systems

FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding

Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs

WebDancer: Towards Autonomous Information Seeking Agency

Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models

Let's Predict Sentence by Sentence

What Makes for Text to 360-degree Panorama Generation with Stable Diffusion?

SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality

Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States

Thinking with Generated Images

CHIMERA: A Knowledge Base of Idea Recombination in Scientific Literature

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment

LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models

Text2Grad: Reinforcement Learning from Natural Language Feedback

Pitfalls of Rule- and Model-based Verifiers -- A Case Study on Mathematical Reasoning

Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction

MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding

One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models

Just as Humans Need Vaccines, So Do Models: Model Immunization to Combat Falsehoods

Styl3R: Instant 3D Stylized Reconstruction for Arbitrary Scenes and Styles

Efficient Data Selection at Scale via Influence Distillation

GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking

Zero-Shot Vision Encoder Grafting via LLM Surrogates

FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control

AITEE -- Agentic Tutor for Electrical Engineering

HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models

Benchmarking Recommendation, Classification, and Tracing Based on Hugging Face Knowledge Graph

Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex

Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese

Right Side Up? Disentangling Orientation Understanding in MLLMs with Fine-grained Multi-axis Perception Tasks

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

Precise In-Parameter Concept Erasure in Large Language Models

Towards Scalable Language-Image Pre-training for 3D Medical Imaging

Can Large Language Models Infer Causal Relationships from Real-World Text?

First Finish Search: Efficient Test-Time Scaling in Large Language Models

IQBench: How "Smart'' Are Vision-Language Models? A Study with Human IQ Tests