Jian Zhang
UC Berkeley / Nexusflow researcher; co-author on Starling-7B and Nectar preference dataset.
- Role
- researcher
- Currently at
- Nexusflow
- Unknown
- GitHub
- Unknown
- Scholar
- scholar.google.com/scholar
- Papers
- 44
Cite
Notes
Only stored in your browser.
Authored papers
44OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
arXiv 2026
TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents
arXiv 2026
MAXS: Meta-Adaptive Exploration with LLM Agents
arXiv 2026
A^3-Bench: Benchmarking Memory-Driven Scientific Reasoning via Anchor and Attractor Activation
arXiv 2026
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
arXiv 2025
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv 2025
DreamO: A Unified Framework for Image Customization
arXiv 2025
MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization
arXiv 2025
MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving
arXiv 2025
Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
arXiv 2025
Quantitative Analysis of Performance Drop in DeepSeek Model Quantization
arXiv 2025
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
arXiv 2025
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
arXiv 2025
GenCompositor: Generative Video Compositing with Diffusion Transformer
arXiv 2025
Fitness aligned structural modeling enables scalable virtual screening with AuroBind
arXiv 2025
Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
arXiv 2025
Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis
arXiv 2025
Fully-Geometric Cross-Attention for Point Cloud Registration
arXiv 2025
Starling-7B: Improving Helpfulness and Harmlessness with RLAIF
ICML
SkillMimic: Learning Basketball Interaction Skills from Demonstrations
CVPR 2025 1
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
arXiv 2024
Adversarial Diffusion Compression for Real-World Image Super-Resolution
CVPR 2025 1
Invertible Diffusion Models for Compressed Sensing
arXiv 2024
DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
CVPR 2024 1
Large Spatial Model: End-to-end Unposed Images to Semantic 3D
arXiv 2024
Retrieval Augmented Instruction Tuning for Open NER with Large Language Models
arXiv 2024
BadEdit: Backdooring large language models by model editing
arXiv 2024
RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians
arXiv 2024
FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models
arXiv 2024
Hybrid Fourier Score Distillation for Efficient One Image to 3D Object Generation
arXiv 2024
Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
arXiv 2024
NetInfoF Framework: Measuring and Exploiting Network Usable Information
arXiv 2024
On the Tool Manipulation Capability of Open-source Large Language Models
arXiv 2023
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
ICCV 2023 1
DomainAdaptor: A Novel Approach to Test-time Adaptation
ICCV 2023 1
EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
arXiv 2023
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
ICCV 2023 1
T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
arXiv 2023
Unlimited-Size Diffusion Restoration
arXiv 2023
AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
arXiv 2023
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
ICCV 2023 1
Implicit Neural Representation for Cooperative Low-light Image Enhancement
ICCV 2023 1
Position Embedding Needs an Independent Layer Normalization
arXiv 2022
EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding
CVPR 2023 1
Affiliations
Frequent co-authors
10from 44 papers