Yifan Zhang
- Papers
- 53
Cite
Notes
Only stored in your browser.
Authored papers
53OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
arXiv 2026
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
arXiv 2026
Deep Delta Learning
arXiv 2026
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
arXiv 2026
PersonaVLM: Long-Term Personalized Multimodal LLMs
arXiv 2026
Interactive Benchmarks
arXiv 2026
How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
arXiv 2026
FlashSampling: Fast and Memory-Efficient Exact Sampling
arXiv 2026
VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining
arXiv 2026
PEARL: Personalized Streaming Video Understanding Model
arXiv 2026
Residual Stream Duality in Modern Transformer Architectures
arXiv 2026
Tensor Product Attention Is All You Need
arXiv 2025
On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
arXiv 2025
FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models
arXiv 2025
Monadic Context Engineering
arXiv 2025
Web World Models
arXiv 2025
Group Representational Position Encoding
arXiv 2025
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
arXiv 2025
Higher-order Linear Attention
arXiv 2025
Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
arXiv 2025
Matrix-Game: Interactive World Foundation Model
arXiv 2025
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
arXiv 2025
Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
arXiv 2025
Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval
arXiv 2025
oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning
arXiv 2025
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
arXiv 2025
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
arXiv 2025
Exact Coset Sampling for Quantum Lattice Algorithms
arXiv 2025
RealGen: Photorealistic Text-to-Image Generation via Detector-Guided Rewards
arXiv 2025
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
arXiv 2025
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
arXiv 2025
DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation
CVPR 2025 1
One-Shot Diffusion Mimicker for Handwritten Text Generation
arXiv 2024
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
arXiv 2024
General Preference Modeling with Preference Representations for Aligning Language Models
arXiv 2024
Poison-splat: Computation Cost Attack on 3D Gaussian Splatting
arXiv 2024
Augmenting Math Word Problems via Iterative Question Composing
arXiv 2024
Training and Evaluating Language Models with Template-based Data Generation
arXiv 2024
On the Diagram of Thought
arXiv 2024
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?
arXiv 2024
Scaling Image Tokenizers with Grouped Spherical Quantization
arXiv 2024
Disentangling Writer and Character Styles for Handwriting Generation
CVPR 2023 1
Meta Prompting for AI Systems
arXiv 2023
Towards Stable Test-Time Adaptation in Dynamic Wild World
arXiv 2023
Cumulative Reasoning with Large Language Models
arXiv 2023
Dataset Quantization
ICCV 2023 1
Contrastive Learning Is Spectral Clustering On Similarity Graph
arXiv 2023
Efficient Test-Time Model Adaptation without Forgetting
arXiv 2022
Expanding Small-Scale Datasets with Guided Imagination
expanding-small-scale-datasets-with-guided
Deep Long-Tailed Learning: A Survey
arXiv 2021
Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition
arXiv 2021
Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
arXiv 2021
Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
NeurIPS 2021 12
Affiliations
Frequent co-authors
10from 53 papers