Artigos de Pesquisa em IA Diários

LoRACode: LoRA Adapters for Code Embeddings

Learning from Failures in Multi-Attempt Reinforcement Learning

Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts

AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM

TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcing Learning

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

SAGE: A Framework of Precise Retrieval for RAG

BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activities

ProReflow: Progressive Reflow with Decomposed Velocity

R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

S2S-Arena, Evaluating Speech2Speech Protocols on Instruction Following with Paralinguistic Information

Forgetting Transformer: Softmax Attention with a Forget Gate

EuroBERT: Scaling Multilingual Encoders for European Languages

RuCCoD: Towards Automated ICD Coding in Russian

LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding

SafeArena: Evaluating the Safety of Autonomous Web Agents

Unified Reward Model for Multimodal Understanding and Generation

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

An Empirical Study on Eliciting and Improving R1-like Reasoning Models

VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control