0

Yang Zhang

Papers
60

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
60papers

Authored papers

60

How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings

arXiv 2026

2026

FlowCompile: An Optimizing Compiler for Structured LLM Workflows

arXiv 2026

2026

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

preprint

2025

R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning

arXiv 2025

2025

Large Language Models for Recommendation with Deliberative User Preference Alignment

arXiv 2025

2025

Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach

arXiv 2025

2025

VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation

arXiv 2025

2025

PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs

arXiv 2025

2025

CommVQ: Commutative Vector Quantization for KV Cache Compression

arXiv 2025

2025

Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction

arXiv 2025

2025

Language-Enhanced Representation Learning for Single-Cell Transcriptomics

arXiv 2025

2025

Steering LLM Thinking with Budget Guidance

arXiv 2025

2025

Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization

arXiv 2025

2025

Towards Interactive Deepfake Analysis

arXiv 2025

2025

Safety at Scale: A Comprehensive Survey of Large Model Safety

arXiv 2025

2025

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

arXiv 2025

2025

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models

arXiv 2025

2025

Fast-Decoding Diffusion Language Models via Progress-Aware Confidence Schedules

arXiv 2025

2025

Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text

arXiv 2025

2025

ScanBot: Towards Intelligent Surface Scanning in Embodied Robotic Systems

arXiv 2025

2025

DeepSeek-V3 Technical Report

arXiv 2024

2024

RULER: What's the Real Context Size of Your Long-Context Language Models?

arXiv 2024

2024

Seed-TTS: A Family of High-Quality Versatile Speech Generation Models

arXiv 2024

2024

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

arXiv 2024

2024

Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming

arXiv 2024

2024

Accurate LoRA-Finetuning Quantization of LLMs via Information Retention

arXiv 2024

2024

PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling

arXiv 2024

2024

Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective

arXiv 2024

2024

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference

arXiv 2024

2024

On the Generalization Ability of Machine-Generated Text Detectors

arXiv 2024

2024

ProgressGym: Alignment with a Millennium of Moral Progress

arXiv 2024

2024

decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points

arXiv 2024

2024

Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models

arXiv 2024

2024

Personalized Image Generation with Large Multimodal Models

arXiv 2024

2024

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning

arXiv 2024

2024

VGMShield: Mitigating Misuse of Video Generative Models

arXiv 2024

2024

Towards Understanding Unsafe Video Generation

arXiv 2024

2024

Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation

arXiv 2024

2024

ModSCAN: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities

arXiv 2024

2024

TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation

arXiv 2023

2023

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

arXiv 2023

2023

Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models

arXiv 2023

2023

A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems

arXiv 2023

2023

AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers

arXiv 2023

2023

Prompt Stealing Attacks Against Text-to-Image Generation Models

arXiv 2023

2023

Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models

arXiv 2023

2023

NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models

arXiv 2023

2023

Correcting Diffusion Generation through Resampling

CVPR 2024 1

2023

Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation

arXiv 2023

2023

Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis

ICCV 2023 1

2023

MGTBench: Benchmarking Machine-Generated Text Detection

arXiv 2023

2023

Generated Graph Detection

arXiv 2023

2023

Linking Emergent and Natural Languages via Corpus Transfer

linking-emergent-and-natural-languages-via

2022

Data Poisoning Attacks Against Multimodal Encoders

arXiv 2022

2022

ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers

arXiv 2022

2022

DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings

NAACL 2022 7

2022

PromptBoosting: Black-Box Text Classification with Ten Forward Passes

arXiv 2022

2022

Model Stealing Attacks Against Inductive Graph Neural Networks

arXiv 2021

2021

AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

arXiv 2019

2019

A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations

a-theoretical-explanation-for-perplexing-1

2018

Affiliations

No known affiliations.

Frequent co-authors

10

from 60 papers