Kai-Wei Chang

30

Papers

4,993

Total Citations

1

Affiliations

Affiliations

UCLA

Papers (30)

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

NeurIPS 2016arXiv

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

VideoPhy: Evaluating Physical Commonsense for Video Generation

VideoCon: Robust Video-Language Alignment via Contrast Captions

STIV: Scalable Text and Image Conditioned Video Generation

A Credit Assignment Compiler for Joint Prediction

NeurIPS 2016arXiv

CoBIT: A Contrastive Bi-directional Image-Text Generation Model

VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

Verbalized Representation Learning for Interpretable Few-Shot Generalization

REVEAL: Retrieval-Augmented Visual-Language Pre-Training With Multi-Source Multimodal Knowledge Memory

On Prompt-Driven Safeguarding for Large Language Models

ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models

Position: TrustLLM: Trustworthiness in Large Language Models

Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension

Grounded Language-Image Pre-Training

GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods

Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering

Controllable Text Generation with Neurally-Decomposed Oracle

Semantic Probabilistic Layers for Neuro-Symbolic Learning

On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs

AVIS: Autonomous Visual Information Seeking with Large Language Model Agent

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints

DesCo: Learning Object Recognition with Rich Language Descriptions

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Learning to Search Better than Your Teacher