Cotbox-ttt: Grounding medical vqa with visual chain- of-thought boxes during test-time training.arXiv preprint arXiv:2511.12446,

Qian, J · arXiv 2511.12446

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

representative citing papers

cs.CV · 2026-06-02 · unverdicted · novelty 6.0

TLVS mitigates hallucinations in LVLMs via token-level extraction and visual-sensitivity-adaptive steering applied only at critical decoding steps.

Showing 1 of 1 citing paper.

Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation cs.CV · 2026-06-02 · unverdicted · none · ref 12
TLVS mitigates hallucinations in LVLMs via token-level extraction and visual-sensitivity-adaptive steering applied only at critical decoding steps.