6 papers
Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift
Pengzhan Sun, Shiu-hong Kao, Shijie Li +4
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human in…
ReSTI: A Source-Grounded Audit and Repair of STI-Bench
Pengzhan Sun, Ramanathan Rajaraman, Shiu-Hong Kao +2
Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit STI-Bench against the officia…
Long-to-Short Video Evidence Reasoning for Grounded Question Answering
Kaiyan Chen, Junbin Xiao, Xun Yang
We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question answering (GQA). LOVER highlight…
Companion-style QA Assistance in Ego-Vision
Hangyu Qin, Junbin Xiao, Shenglang Zhang +1
AI companions are envisioned as always-on assistants that support users in daily life. With this regard, we introduce BuddyVQA, a benchmark for companion-style question answering (…
Keep It in Mind: User Centric Continual Spatial Intelligence Reasoning in Egocentric Video Streams
Yun Wang, Junbin Xiao, Han Lyu +6
We introduce UCS-Bench, a dataset spanning 170+ hours of egocentric visual observations with 8.1K+ timestamped questions for diagnosing User-Centric Continual Spatial intelligence…
EgoExo-Con: Exploring View-Invariant Video Temporal Understanding
Minjoon Jung, Junbin Xiao, Junghyun Kim +2
Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introduce EgoExo-Con(sistency), a benc…