AI Onderzoekspapers Dagelijks

Chain-of-Model Learning for Language Model

AdaptThink: Reasoning Models Can Learn When to Think

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

Thinkless: LLM Learns When to Think

Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis

Faster Video Diffusion with Trainable Sparse Attention

Model Merging in Pre-training of Large Language Models

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images

Hybrid 3D-4D Gaussian Splatting for Fast Dynamic Scene Representation

MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision

CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models

FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA

Fractured Chain-of-Thought Reasoning

EfficientLLM: Efficiency in Large Language Models

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning

Neuro-Symbolic Query Compiler

ViPlan: A Benchmark for Visual Planning with Symbolic Predicates and Vision-Language Models

R3: Robust Rubric-Agnostic Reward Models

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space

Accelerate TarFlow Sampling with GS-Jacobi Iteration

MTVCrafter: 4D Motion Tokenization for Open-World Human Image Animation

Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation

SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning

FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance

QVGen: Pushing the Limit of Quantized Video Generative Models

ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning

HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology

MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports

Creating General User Models from Computer Use

From Grunts to Grammar: Emergent Language from Cooperative Foraging

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Learned Lightweight Smartphone ISP with Unpaired Data

LLM Context Conditioning and PWP Prompting for Multimodal Validation of Chemical Formulas

Can AI Freelancers Compete? Benchmarking Earnings, Reliability, and Task Success at Scale

AI-Driven Scholarly Peer Review via Persistent Workflow Prompting, Meta-Prompting, and Meta-Reasoning

Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models