Joseph Gonzalez

papers

812

total citations

papers (15)

From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

ICML 2025arXiv

357

citations

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

NEURIPS 2025arXiv

citations

SimpleStrat: Diversifying Language Model Generation with Stratification

NEURIPS 2025arXiv

citations

See Say and Segment: Teaching LMMs to Overcome False Premises

CVPR 2024

citations

Discovering Divergent Representations between Text-to-Image Models

ICCV 2025arXiv

citations

Joseph Gonzalez

papers (15)

From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

Self-correcting LLM-controlled Diffusion Models

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

How to Evaluate Reward Models for RLHF

Describing Differences in Image Sets with Natural Language

LLM-Assisted Code Cleaning For Training Accurate Code Generators

On Guiding Visual Attention With Language Specification

RouteLLM: Learning to Route LLMs from Preference Data

VisionArena: 230k Real World User-VLM Conversations with Preference Labels

Context-Aware Streaming Perception in Dynamic Environments

HashAttention: Semantic Sparsity for Faster Inference

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

SimpleStrat: Diversifying Language Model Generation with Stratification

See Say and Segment: Teaching LMMs to Overcome False Premises

Discovering Divergent Representations between Text-to-Image Models

papers (15)

From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline

Self-correcting LLM-controlled Diffusion Models

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

How to Evaluate Reward Models for RLHF

Describing Differences in Image Sets with Natural Language

LLM-Assisted Code Cleaning For Training Accurate Code Generators

On Guiding Visual Attention With Language Specification

RouteLLM: Learning to Route LLMs from Preference Data

VisionArena: 230k Real World User-VLM Conversations with Preference Labels

Context-Aware Streaming Perception in Dynamic Environments

HashAttention: Semantic Sparsity for Faster Inference

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

SimpleStrat: Diversifying Language Model Generation with Stratification

See Say and Segment: Teaching LMMs to Overcome False Premises

Discovering Divergent Representations between Text-to-Image Models