3 papers
cs.LG2026
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin +4
Language-model agents act through structured tool calls whose arguments carry very different risks: untrusted content may legitimately shape an email body but should never set a re…
cs.CV2026
Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models
Niamul Hassan Samin, Md Arifur Rahman, Abdullah Ibne Hanif Arean +2
Vision-Language Models (VLMs) often hallucinate objects that are not present in the input image. We identify a contributing cause of this behavior, which we term spatial credit col…
cs.CV2026
Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models
Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin +2
We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better. Standard benchmarks measure only final-answe…