Tag
Periscope introduces a training-free inference method that arranges text chunks on a K×K grid and queries a frozen language model over local and strided spans to recover answers beyond the context window, matching or beating full-window reads on LongBench v2 and InfiniteBench at a fraction of the cost. The approach lets a 27B model read 4.5M-token contexts on a single 80GB GPU by replacing long reads with an evidence map.
This paper diagnoses perceptual-decision misalignment in Omni-LLMs and proposes a training-free inference-time framework called Modality Subspace Activation to mitigate it by dynamically balancing modality strengths.
This paper introduces Positive-and-Negative Decoding (PND), a training-free inference framework that reduces object hallucination in Vision-Language Models by contrasting positive visual evidence with negative counterfactuals during decoding.