Tag: spatio-temporal reasoning
Browse our exclusive articles!
PushupBench Reveals VLMs Fail to Count Pushups Accurately
PushupBench dataset exposes large vision-language models' struggle to count pushup reps, highlighting the need for better temporal reasoning in AI video an...
PhysNote: Enhancing Physical Reasoning in Vision-Language AI
Discover PhysNote, a new framework boosting Vision-Language Models' physical reasoning with improved consistency and knowledge retention.
Dual-Trace Encoding Boosts Cross-Session Recall in LLM Agents
Discover how dual-trace encoding enhances cross-session memory recall in LLM agents, improving temporal reasoning and knowledge tracking by 20%.
Progressive Training to Fix Vision-Language Model Hallucinations
Discover a progressive training strategy that reduces spatio-temporal hallucinations in vision-language models, boosting dynamic reasoning accuracy.