Jun Zhu
- Papers
- 61
Cite
Notes
Only stored in your browser.
Authored papers
61KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
arXiv 2026
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
arXiv 2026
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
arXiv 2026
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
arXiv 2026
Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection
arXiv 2026
SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training
arXiv 2025
SageAttention2++: A More Efficient Implementation of SageAttention2
arXiv 2025
ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
arXiv 2025
RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
arXiv 2025
Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
direct-discriminative-optimization-your
Scaling Diffusion Transformers Efficiently via $μ$P
arXiv 2025
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
arXiv 2025
UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers
arXiv 2025
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
arXiv 2025
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
arXiv 2025
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
arXiv 2025
SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
arXiv 2025
DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
ICCV 2025
Robust Representation Consistency Model via Contrastive Denoising
arXiv 2025
STAIR: Improving Safety Alignment with Introspective Reasoning
arXiv 2025
Visual Generation Without Guidance
arXiv 2025
MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
ICCV 2025
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
arXiv 2024
Pruning Large Language Models with Semi-Structural Adaptive Sparse Training
arXiv 2024
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
arXiv 2024
Efficient Backpropagation with Variance-Controlled Adaptive Sampling
arXiv 2024
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
arXiv 2024
CodeS: Towards Building Open-source Language Models for Text-to-SQL
arXiv 2024
MicroDreamer: Efficient 3D Generation in $\sim$20 Seconds by Score-based Iterative Reconstruction
arXiv 2024
ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
arXiv 2024
Diffusion Bridge Implicit Models
arXiv 2024
FlexiDreamer: Single Image-to-3D Generation with FlexiCubes
arXiv 2024
DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
arXiv 2024
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization
arXiv 2024
Noise Contrastive Alignment of Language Models with Explicit Rewards
arXiv 2024
Towards Efficient Exact Optimization of Language Model Alignment
arXiv 2024
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
arXiv 2023
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
diffusion-models-and-semi-supervised-learners
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
arXiv 2023
NUNO: A General Framework for Learning Parametric PDEs with Non-Uniform Data
arXiv 2023
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
arXiv 2023
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
arXiv 2023
Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
arXiv 2023
Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation
overcoming-recency-bias-of-normalization
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
arXiv 2023
LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
arXiv 2023
Detection Transformer with Stable Matching
ICCV 2023 1
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
arXiv 2023
Training Transformers with 4-bit Integers
training-transformers-with-4-bit-integers
DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics
dpm-solver-v3-improved-diffusion-ode-solver
A Comprehensive Survey of Continual Learning: Theory, Method and Application
arXiv 2023
GNOT: A General Neural Operator Transformer for Operator Learning
arXiv 2023
Score Regularized Policy Optimization through Diffusion Behavior
arXiv 2023
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
arXiv 2023
Rethinking Model Ensemble in Transfer-based Adversarial Attacks
arXiv 2023
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
dino-detr-with-improved-denoising-anchor
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
arXiv 2022
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR
dab-detr-dynamic-anchor-boxes-are-better
Robustness and Accuracy Could Be Reconcilable by (Proper) Definition
arXiv 2022
Counter-Strike Deathmatch with Large-Scale Behavioural Cloning
arXiv 2021
Adversarial Attacks and Defences Competition
arXiv 2018
Affiliations
Frequent co-authors
10from 61 papers