Papers by Winston H. Hsu

4 papers
MovieCORE: COgnitive REasoning in Movies (2025.emnlp-main)

Copied to clipboard

Challenge: MovieCORE is a video question answering dataset that focuses on surface-level comprehension.
Approach: They propose a video question-answer dataset that uses large language models as thought agents to generate and refine high-quality question-anchor pairs.
Outcome: The proposed model improves model reasoning capabilities post-training by 25% . the proposed model is based on a large language model and is scalable to a wide range of tasks .
Attention Tracker: Detecting Prompt Injection Attacks in LLMs (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated actions.
Approach: They propose a training-free method that tracks attention patterns on instruction to detect prompt injection attacks without additional inference.
Outcome: The proposed method shows an improvement of up to 10.0% over existing methods and performs well even on small LLMs.
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for embodied agents focus on directly executing instructions without considering whether objects can be manipulated.
Approach: They propose a benchmark that evaluates embodied agents in dynamic environments . they use plug-and-play module that augments existing planners with explicit affordance reasoning .
Outcome: The proposed benchmark evaluates embodied agents in dynamic environments with unpredictable affordances . ADAPT significantly improves robustness and task success across seen and unseen environments .
VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions (2026.acl-long)

Copied to clipboard

Challenge: Existing Vision-and-Language Navigation benchmarks assume instructions are feasible and the referenced target exists.
Approach: They propose a benchmark with false-premise instructions where the target is absent . they propose supervised room-level navigation with LLM/VLM-driven in-room exploration .
Outcome: The proposed benchmark produces false-premise goals that are plausible but factually incorrect . ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations