Zhangyang Wang
- Papers
- 76
Cite
Notes
Only stored in your browser.
Authored papers
76MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
arXiv 2026
nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
arXiv 2026
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
arXiv 2026
GradientStabilizer:Fix the Norm, Not the Gradient
arXiv 2025
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
arXiv 2025
Enhance-A-Video: Better Generated Video for Free
arXiv 2025
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
arXiv 2025
SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
arXiv 2025
Steepest Descent Density Control for Compact 3D Gaussian Splatting
CVPR 2025 1
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
arXiv 2025
LLMs Can Get "Brain Rot"!
arXiv 2025
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
arXiv 2025
Can Test-Time Scaling Improve World Foundation Model?
arXiv 2025
Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding
arXiv 2025
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
arXiv 2025
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
arXiv 2025
SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training
arXiv 2025
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds
arXiv 2024
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
arXiv 2024
Large Spatial Model: End-to-end Unposed Images to Semantic 3D
arXiv 2024
LLaGA: Large Language and Graph Assistant
arXiv 2024
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
CVPR 2025 1
LoCoCo: Dropping In Convolutions for Long Context Compression
arXiv 2024
Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
arXiv 2024
Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
arXiv 2024
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
arXiv 2024
Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
arXiv 2024
Principled Architecture-aware Scaling of Hyperparameters
arXiv 2024
APOLLO: SGD-like Memory, AdamW-level Performance
arXiv 2024
Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients
arXiv 2024
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
arXiv 2024
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
arXiv 2024
Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
arXiv 2024
From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients
arXiv 2024
AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
arXiv 2024
On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability
arXiv 2024
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
arXiv 2024
OpenBias: Open-set Bias Detection in Text-to-Image Generative Models
CVPR 2024 1
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
arXiv 2023
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
ICCV 2023 1
PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editor
arXiv 2023
Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?
arXiv 2023
Towards Constituting Mathematical Structures for Learning to Optimize
arXiv 2023
The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter
the-emergence-of-essential-sparsity-in-large
Safe and Robust Watermark Injection with a Single OoD Image
arXiv 2023
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
arXiv 2023
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models
CVPR 2024 1
Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
CVPR 2024 1
In-Context Learning Unlocked for Diffusion Models
in-context-learning-unlocked-for-diffusion
HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models
arXiv 2023
Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts
arXiv 2023
Robust Mixture-of-Expert Training for Convolutional Neural Networks
ICCV 2023 1
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
arXiv 2023
Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts
ICCV 2023 1
DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
arXiv 2023
Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
arXiv 2023
Compressing LLMs: The Truth is Rarely Pure and Never Simple
arXiv 2023
Physics-Driven Turbulence Image Restoration with Stochastic Refinement
ICCV 2023 1
Equivariant Hypergraph Diffusion Neural Operators
arXiv 2022
Versatile Diffusion: Text, Images and Variations All in One Diffusion Model
ICCV 2023 1
APP: Anytime Progressive Pruning
arXiv 2022
E^2TAD: An Energy-Efficient Tracking-based Action Detector
arXiv 2022
NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views
arXiv 2022
M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
arXiv 2022
Auto-scaling Vision Transformers without Training
auto-scaling-vision-transformers-without
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
the-unreasonable-effectiveness-of-random
Unified Visual Transformer Compression
unified-visual-transformer-compression
Neural Implicit Dictionary via Mixture-of-Expert Training
arXiv 2022
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
dsee-dually-sparsity-embedded-efficient
Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
sparse-training-via-boosting-pruning-1
You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership
NeurIPS 2021 12
Hyperparameter Tuning is All You Need for LISTA
NeurIPS 2021 12
Graph Contrastive Learning with Augmentations
NeurIPS 2020 12
When Does Self-Supervision Help Graph Convolutional Networks?
ICML 2020 1
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
deblurgan-v2-deblurring-orders-of-magnitude-1
EnlightenGAN: Deep Light Enhancement without Paired Supervision
arXiv 2019
Affiliations
Frequent co-authors
10from 76 papers