ReToken: One Token to Improve Vision-Language Models for Visual Retrieval
Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints. We present ReToken, a single learnable embedding trained as an explicit retrieval target that selects a sparse set of query-relevant visual tokens from a pre-filled visual KV cache.…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
