Jun Wang

The paper proposes a novel method to inject reliable, sustained backdoors into LLMs by compiling an activation steering vector into model weights, ensuring the backdoor only activates upon a specific trigger.

GS-Fuse is a novel multimodal framework that improves financial forecasting by adaptively fusing event text and price data, achieving state-of-the-art performance by explicitly modeling the directional, causal relationship between events and market movements.

GS-Fuse is a novel multimodal framework that improves financial forecasting by adaptively fusing event text and price data, achieving state-of-the-art performance by explicitly modeling the directional, causal relationship between events and market movements.

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) are unreliable for safe human-robot collaboration.

The paper introduces SPIRE, a multi-agent framework designed to extend LLM research capabilities to the humanities by enabling evidence-grounded interpretive reasoning over primary sources.

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) are unreliable for safe human-robot collaboration.

The paper introduces SPIRE, a multi-agent framework designed to extend LLM research capabilities to the humanities by enabling evidence-grounded interpretive reasoning over primary sources.

This paper introduces EvoArena, a benchmark suite for evaluating large language model agents in dynamic environments, and EvoMem, a patch-based memory paradigm that improves performance in these environments.

This paper argues that large language models have fundamental limitations as general-purpose solvers due to the capacity-limited nature of language as a communication channel and alignment constraints.

The paper presents Ropedia W0, a world model that enables embodied agents to anticipate action consequences across diverse embodiments.

This paper introduces Continual Learning Exam (CLE), a large-scale benchmark to measure experience-driven improvement in LLM agents.