Fu

26

Papers

388

Total Citations

Papers (26)

UMA: A Family of Universal Models for Atoms

NeurIPS 2025arXiv

Hymba: A Hybrid-head Architecture for Small Language Models

Vision Language Models are In-Context Value Learners

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

SWE-bench Goes Live!

NeurIPS 2025arXiv

Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

NeurIPS 2025arXiv

Is Artificial Intelligence Generated Image Detection a Solved Problem?

NeurIPS 2025arXiv

Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports

Learning-Augmented Search Data Structures

Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence

NeurIPS 2025arXiv

Not-So-Optimal Transport Flows for 3D Point Cloud Generation

Exploring Diffusion Transformer Designs via Grafting

NeurIPS 2025arXiv

ThunderKittens: Simple, Fast, and $\textit{Adorable}$ Kernels

Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time

NeurIPS 2025arXiv

COS3D: Collaborative Open-Vocabulary 3D Segmentation

NeurIPS 2025arXiv

From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction

NeurIPS 2025arXiv

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

NeurIPS 2025arXiv

Towards Reliable and Holistic Visual In-Context Learning Prompt Selection

NeurIPS 2025arXiv

Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays

ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection

NeurIPS 2025arXiv

VisualLens: Personalization through Task-Agnostic Visual History

NeurIPS 2025arXiv

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

NeurIPS 2025arXiv