REVIEW 5 cited by
IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
read the original abstract
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated significant progress across multiple domains. However, these models still face the inherent challenge of integrating vision and language for collaborative inference, which often leads to "hallucinations", outputs that are not grounded in the corresponding images. Many efforts have been made to address these issues, but each comes with its own limitations, such as high computational cost or expensive dataset annotation. Recent research shows that LVLMs exhibit a long-term bias where hallucinations increase as the sequence length grows, yet the underlying cause remains poorly understood. Building on extensive research into attention mechanisms in LVLMs, we analyze the relationship between this long-term bias and visual attention. In our research, we identify a consistent phenomenon in current LVLMs: the model's attention to visual input diminishes as the generated sequence grows, which we hypothesize to be a key factor contributing to observed increasing hallucinations. Based on these insights, we propose Image attention-guided Key-value merging cOllaborative Decoding (IKOD), a collaborative decoding strategy generating more image-focused sequences. This method derives logits from shorter sequences with higher image attention through key-value merging and combines them with those from the original decoding, effectively mitigating attention degradation and suppressing hallucinations while not incurring too much inference cost. Extensive experiments on both hallucination and comprehensive benchmarks demonstrate IKOD's superior effectiveness in mitigating hallucinations and improving comprehensive capacities for LVLMs. Importantly, IKOD requires no additional training or external tools, making it a lightweight and efficient framework applicable to various models.
Forward citations
Cited by 5 Pith papers
-
C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs
C-PTQ weights quantization error by per-channel Fisher information of the task loss, improving low-bit accuracy of multimodal LLMs by small margins over existing channel-wise scaling methods.
-
Visual Access Boundaries in Vision-Language Model Reasoning
CoT in VLMs extends language-side computation over early image-derived states rather than prolonging direct image-token access, with gains limited by perceptual readout reliability.
-
Visual Access Boundaries in Vision-Language Model Reasoning
Chain-of-thought in VLMs does not require prolonged direct image-token attention; the visual-access boundary stays roughly fixed while generation grows, and CoT gains are gated by perceptual readout.
-
Attention Degradation, Function Token Anchoring, and the Limits of Attention-Based Intervention in Large Language Models
In GPT-2, OPT-1.3B, and LLaMA-3.2 models, boosting attention to function-token positions by 16-24% does not improve contextual retrieval, so short-range attention degradation is descriptive rather than causal.
-
StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning
StochasT uses stochastic clustering of language tasks into varying turn depths for the same image to improve LVLMs on both single-turn and multi-turn scenarios without discarding data.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.