Bo Li

154

Papers

1,637

Total Citations

Papers (154)

Depth and Surface Normal Estimation From Monocular Images Using Regression on Deep Features and Hierarchical CRFs

Data Poisoning Attacks on Factorization-Based Collaborative Filtering

NeurIPS 2016arXiv

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

Revisiting Single Image Reflection Removal In the Wild

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

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

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

ASAM: Boosting Segment Anything Model with Adversarial Tuning

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

Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

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

Relative Pose Estimation of Calibrated Cameras with Known SE(3) Invariants

Reliable and Efficient Amortized Model-based Evaluation

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

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

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

Boosting Adversarial Transferability with Spatial Adversarial Alignment

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

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

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Recognizing Car Fluents From Video

Multi-View 3D Object Detection Network for Autonomous Driving

Robust Physical-World Attacks on Deep Learning Visual Classification

High Performance Visual Tracking With Siamese Region Proposal Network

SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks

MeshAdv: Adversarial Meshes for Visual Recognition

Deep Incremental Hashing Network for Efficient Image Retrieval

Generating 3D Adversarial Point Clouds

The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Controllable Orthogonalization in Training DNNs

Referring Image Segmentation via Cross-Modal Progressive Comprehension

A Real-Time Cross-Modality Correlation Filtering Method for Referring Expression Comprehension

UnrealPerson: An Adaptive Pipeline Towards Costless Person Re-Identification

Scalability vs. Utility: Do We Have To Sacrifice One for the Other in Data Importance Quantification?

Learning Invariant Representations and Risks for Semi-Supervised Domain Adaptation

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

Detecting Camouflaged Object in Frequency Domain

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

Unsupervised Learning of Accurate Siamese Tracking

Equalized Focal Loss for Dense Long-Tailed Object Detection

Towards Efficient Data Free Black-Box Adversarial Attack

Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning

Cross Domain Object Detection by Target-Perceived Dual Branch Distillation

Towards Practical Certifiable Patch Defense With Vision Transformer

Efficient Multi-View Stereo by Iterative Dynamic Cost Volume

Graph Transformer GANs for Graph-Constrained House Generation

PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification

On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data

TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets

Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models

Panoptic Video Scene Graph Generation

Dual Alignment Unsupervised Domain Adaptation for Video-Text Retrieval

PointCloud Saliency Maps

AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos

Group-Wise Deep Object Co-Segmentation With Co-Attention Recurrent Neural Network

Disentangled High Quality Salient Object Detection

Energy-Based Open-World Uncertainty Modeling for Confidence Calibration

Can Shape Structure Features Improve Model Robustness Under Diverse Adversarial Settings?

AREA: Adaptive Reweighting via Effective Area for Long-Tailed Classification

LRRU: Long-short Range Recurrent Updating Networks for Depth Completion

Efficient Decision-based Black-box Patch Attacks on Video Recognition

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

Shape Matters: Deformable Patch Attack

SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination

Backbone Is All Your Need: A Simplified Architecture for Visual Object Tracking

Doubly-Fused ViT: Fuse Information from Vision Transformer Doubly with Local Representation

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

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

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

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

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

Multi-source Domain Adaptation for Semantic Segmentation

On Convergence of Nearest Neighbor Classifiers over Feature Transformations

Counterfactual Prediction for Bundle Treatment

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators

Anti-Backdoor Learning: Training Clean Models on Poisoned Data

Adversarial Attack Generation Empowered by Min-Max Optimization

TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness

Integrated Latent Heterogeneity and Invariance Learning in Kernel Space

Fair Scheduling for Time-dependent Resources

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?

Fairness in Federated Learning via Core-Stability

Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

Exact Shape Correspondence via 2D graph convolution

LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness

AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

DENSE: Data-Free One-Shot Federated Learning

Product Ranking for Revenue Maximization with Multiple Purchases

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning

CoPur: Certifiably Robust Collaborative Inference via Feature Purification

Certifying Some Distributional Fairness with Subpopulation Decomposition

OpenOOD: Benchmarking Generalized Out-of-Distribution Detection

Distributionally Robust Optimization with Data Geometry

Improving Certified Robustness via Statistical Learning with Logical Reasoning

Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization

Continuous Parametric Optical Flow

WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Optimized Covariance Design for AB Test on Social Network under Interference

An Inductive Bias for Tabular Deep Learning

Content-based Unrestricted Adversarial Attack

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

Fair Allocation of Indivisible Chores: Beyond Additive Costs

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand

Large Language Models are Visual Reasoning Coordinators

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

Robust Inference via Generative Classifiers for Handling Noisy Labels