Knowledge Node v26.3 Neural Research

AI Papers Library

The cutting edge of artificial intelligence research. Sharded from the global knowledge mesh and verified via ArXiv and Papers With Code.

Classifier-Free Diffusion Guidance

72 FNI

OPT: Open Pre-trained Transformer Language Models

71 FNI

Federated Learning: Collaborative Machine Learning without Centralized Training Data

69 FNI

A Mechanistic View on Video Generation as World Models: State and Dynamics

39 FNI

MirrorBench: An Extensible Framework to Evaluate User-Proxy Agents for Human-Likeness

39 FNI

DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems

39 FNI

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning

39 FNI

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer

39 FNI

AACR-Bench: Evaluating Automatic Code Review with Holistic Repository-Level Context

39 FNI

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

39 FNI

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

39 FNI

FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights

39 FNI

CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs

39 FNI

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

39 FNI

VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?

39 FNI

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning

39 FNI

Uncovering Cross-Objective Interference in Multi-Objective Alignment

39 FNI

Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

39 FNI

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

39 FNI

UniWeTok: An Unified Binary Tokenizer with Codebook Size 2^{128} for Unified Multimodal Large Language Model

39 FNI

V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation

39 FNI

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding

39 FNI

Motivation in Large Language Models

39 FNI

Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching

39 FNI

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

39 FNI

S2D2: Fast Decoding for Diffusion LLMs via Training-Free Self-Speculation

39 FNI

Test-Time Scaling Makes Overtraining Compute-Optimal

39 FNI

CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning

39 FNI

RewardFlow: Generate Images by Optimizing What You Reward

39 FNI

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

39 FNI

VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction

39 FNI

Rethinking Training Dynamics in Scale-wise Autoregressive Generation

39 FNI

Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning

39 FNI

Reinforcement Learning for Self-Improving Agent with Skill Library

39 FNI

Video-BrowseComp: Benchmarking Agentic Video Research on Open Web

39 FNI

Scaling Open-Ended Reasoning to Predict the Future

39 FNI

2011.09534

38 FNI

2410.14127

38 FNI

2509.25175

38 FNI

2510.00579

38 FNI

2510.01902

38 FNI

2510.21739

38 FNI

2511.08133

38 FNI

2511.08915

38 FNI

2511.09540

38 FNI

2511.10074

38 FNI

2511.10648

38 FNI

2511.11077

38 FNI