fuse-clip-object-logits-lvlm-entropy-decoding TEC-0263 · proposedFuse CLIP object logits by LVLM entropy at decoding
At each decoding step, pick object tokens among the top-k candidates with WordNet, rescore them with CLIP similarity to the image, rescale the scores into the LVLM logit range, and blend the two with a weight equal to the LVLM's normalized
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
At each decoding step, pick object tokens among the top-k candidates with WordNet, rescore them with CLIP similarity to the image, rescale the scores into the LVLM logit range, and blend the two with a weight equal to the LVLM's normalized Filed by the drafting stage from Test-Time Hallucination Control in Large Vision-Language Models (2608.11474) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: CHAIR_S/CHAIR_I and BLEU on 500 MSCOCO images over three seeds, OPOPE accuracy/precision/F1, and GPT-4V scores on LLaVA-Bench, against greedy, beam, DoLa, OPERA, VCD, HALC, Woodpecker, LURE and Nullu; reported CHAIR_S 14.27 vs 15.20 (Nullu) and 20.40 (greedy) on LLaVA-1.5, with throughput 0.59 vs 0.72 items/s for greedy; ablations sweep the fixed coefficient and the candidate-pool size (best at 10).. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.