Bo Li

59

Papers

636

Total Citations

Papers (59)

Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

Revisiting Single Image Reflection Removal In the Wild

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models

ASAM: Boosting Segment Anything Model with Adversarial Tuning

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

NeurIPS 2025arXiv

CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

NeurIPS 2025arXiv

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?

Reliable and Efficient Amortized Model-based Evaluation

Learning Adaptive Lighting via Channel-Aware Guidance

Envy-Free House Allocation under Uncertain Preferences

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks

Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning

Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources

Boosting Adversarial Transferability with Spatial Adversarial Alignment

ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning

COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems Against Semantic Attacks

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

GRATH: Gradual Self-Truthifying for Large Language Models

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

Certifiably Byzantine-Robust Federated Conformal Prediction

Improved Bounds for Pure Private Agnostic Learning: Item-Level and User-Level Privacy

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications

Fair Federated Learning via the Proportional Veto Core

InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining

SHINE: Shielding Backdoors in Deep Reinforcement Learning

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

EgoLife: Towards Egocentric Life Assistant

LGA-Net: Learning Local and Global Affinities for Sparse Scribble based Image Colorization

Large Multi-modal Models Can Interpret Features in Large Multi-modal Models

MOERL: When Mixture-of-Experts Meet Reinforcement Learning for Adverse Weather Image Restoration

SDMatte: Grafting Diffusion Models for Interactive Matting

Diversity-Enhanced Distribution Alignment for Dataset Distillation

Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study

Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning

Boosting Vision State Space Model with Fractal Scanning

DiffScene: Diffusion-Based Safety-Critical Scenario Generation for Autonomous Vehicles

HFF-Tracker: A Hierarchical Fine-grained Fusion Tracker for Referring Multi-Object Tracking

Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking

The (Exact) Price of Cardinality for Indivisible Goods: A Parametric Perspective

MalDetectFormer: Leveraging Sparse SpatioTemporal Information for Effective Malicious Traffic Detection

Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles

MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos

Re-thinking Data Availability Attacks Against Deep Neural Networks

Multi-Task Dense Prediction via Mixture of Low-Rank Experts

Improving Depth Completion via Depth Feature Upsampling

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Improving Adversarial Energy-Based Model via Diffusion Process