Jing Huang

20

Papers

138

Total Citations

1

Affiliations

Affiliations

Stanford University

Papers (20)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Real-Time Simulated Avatar from Head-Mounted Sensors

MIB: A Mechanistic Interpretability Benchmark

LLMs Encode Harmfulness and Refusal Separately

NeurIPS 2025arXiv

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling

MoLE:Decoding by Mixture of Layer Experts Alleviates Hallucination in Large Vision-Language Models

Blackbox Model Provenance via Palimpsestic Membership Inference

NeurIPS 2025arXiv

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation

PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision

Crowd3D: Towards Hundreds of People Reconstruction From a Single Image

Self-Supervised Object Detection from Egocentric Videos

Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting

Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection

RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters

A Plug-and-Play Bregman ADMM Module for Inferring Event Branches in Temporal Point Processes

Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

A Multiplexed Network for End-to-End, Multilingual OCR

TextOCR: Towards Large-Scale End-to-End Reasoning for Arbitrary-Shaped Scene Text

Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization