3 papers
cs.LG2026
Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models
Weihan Li, Junhao Wu, Xinlei Chen +1
Language models can produce similar probabilistic predictions after observing outcomes, reading summaries, receiving instructions, or undergoing activation interventions. Whether t…
cs.CV2026
How Does Geometry Enter Generated Motion?
Weihan Li, Junhao Wu, Yuhan Song +2
Under a fixed physical law, the visible geometry of a scene determines how motion must change. We ask how video generators realize this relationship. We fix the law and the initial…
cs.LG2026
Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
Weihan Li, Xinlei Chen, Yuhan Song +2
Claims about what an internal direction in an LLM represents need evidential constraints beyond an observer's prior beliefs about the system. Decodability and successful activation…