CoFFT: Chain of Foresight-Focus Thought for Visual Language Models¶
🕒 Published (v1): 2025-01-01 · Source: NeurIPS · Venue: NeurIPS 2025 · link
Ask a follow-up
Open an assistant pre-loaded with this paper's context.
💬 Ask ChatGPT✦ Ask Claude
TL;DR¶
CoFFT is a training-free inference-time framework that improves VLM visual reasoning by emulating human visual cognition: iteratively generating diverse reasoning samples, selecting the best via joint visual-focus and reasoning-progression scoring, then zooming into the most relevant image region before the next reasoning step. Applied to Qwen2.5-VL, InternVL2.5, and LLaVA-Next, it yields consistent 3.1–5.8% average accuracy gains across seven benchmarks with lower compute cost than MCTS.
Problem¶
VLMs are easily distracted by visually dominant but semantically irrelevant image content, causing hallucinations and task-irrelevant reasoning. Existing approaches either fix visual focus to a single pass (DyFo, ICoT) or apply text-only search (MCTS, Predictive Decoding) without dynamically steering attention to task-critical regions during multi-step reasoning.
Method¶
CoFFT iterates a three-stage loop per reasoning step:
-
Diverse Sample Generation (DSG): The VLM generates k candidate next-step bundles using temperature sampling (0.4–1.0), each containing up to l foresight reasoning steps.
-
Dual Foresight Decoding (DFD): Each candidate is scored by a combined metric
E = λ·Eatt + (1−λ)·Eprob(λ=0.3).Eattmeasures visual coherence via cosine similarity and IoU of top-30% attention regions between the question's relative attention map and the sample's attention map.Eprobmeasures average log-probability improvement across the l steps relative to the baseline reasoning process. The first step of the top-scoring candidate is appended to the reasoning chain. -
Visual Focus Adjustment (VFA): A dual-criteria attention map
Acropis built from (a) question-relevance attention minus already-explored regions (C_rel(V,Q,R_t)) and (b) future-reasoning attention from the selected sample (A_rel(V,s_i)). A sliding window searches regions spanning 40–90% of the original image dimensions and selects the highest-mean-attention crop, subject to an adaptive thresholdβthat tightens when the two criteria diverge. The crop is upscaled as the next iteration's visual input.
Relative attention normalization (A_rel = Softmax(A(V,Q) / (A(V,D) + ε))) suppresses globally salient but question-irrelevant features throughout.
Key Contributions¶
- Training-free iterative visual reasoning loop that couples dynamic image cropping with multi-sample reasoning selection.
- Dual Foresight Decoding: joint visual-focus score (cosine + IoU of attention maps) and reasoning-progression score (mean log-prob delta across foresight steps).
- Visual Focus Adjustment with adaptive thresholding that switches between global and local views without requiring extra models or segmentation modules.
- Demonstrated positive scaling: absolute gains increase from 7B to 32B backbone models.
- Two new geography-VQA datasets: SeekWorld-China and SeekWorld-Global.
Results¶
- CoFFT (Qwen2.5-VL-7B): 48.19% avg vs. 42.72% baseline, 44.68% MCTS, 45.05% Predictive Decoding, 34.91% DyFo, 44.98% ICoT across 7 benchmarks.
- CoFFT (Qwen2.5-VL-32B): 52.96% avg vs. 47.05% baseline; largest gains on SeekWorld-China (38.61% vs. 24.13%) and MathVision (29.93% vs. 25.33%).
- CoFFT (InternVL2.5-8B): 45.30% avg vs. 40.84% baseline.
- CoFFT (LLaVA-Next-7B): 25.54% avg vs. 22.41% baseline.
- FLOPS (Qwen2.5-VL-7B): CoFFT = 2.38e+14 vs. MCTS = 4.05e+14 (42% cheaper than MCTS) vs. baseline = 8.35e+12.
- Ablation: removing DFD drops avg by ~2.4%; removing VFA drops avg by ~2.5%, with largest hits on SeekWorld and Charxiv.
- Still underperforms GPT-4o and Gemini-2.0-Flash on SeekWorld-Global (29.37% vs. ~55–56%).
Limitations¶
- Can introduce new errors on problems the base VLM already solves correctly (reasoning interference).
- Significant compute overhead over greedy baseline (~28× in FLOPS), making real-time deployment costly.
- Performance on SeekWorld-Global still lags closed-source models, attributed to limited regional geographic knowledge in open-source pretraining data.
- Hyperparameter sensitivity: performance and cost grow with l and k; optimal values require benchmark-specific tuning.
- Relies on VLM-internal attention maps, which may be noisy for models with non-standard architectures or sparse-attention variants.
Relevance to Vision-Language Models¶
CoFFT directly addresses one of the core failure modes of current VLMs—susceptibility to visually salient but task-irrelevant distractors—by coupling the reasoning chain to dynamic, attention-guided image cropping at inference time. It connects to the growing body of test-time compute scaling work (MCTS, Predictive Decoding) but uniquely integrates visual grounding as a first-class signal in the search process rather than treating it post-hoc. The positive scaling trend with model size suggests the method becomes more valuable as base VLMs improve, making it relevant to any researcher studying multimodal reasoning, hallucination reduction, or inference-time augmentation for VLMs.