arXiv AI
Emergent Goal-Directed Attention in Large Vision-Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 16
Attention, not scale, drives human-AI alignment in multimodal language prediction
arXiv:2308. 06035v4 Announce Type: replace Abstract: Humans routinely draw on visual context to predict upcoming words.
arXiv AI
Aug 18
Matched Outcomes, Divergent Gaze: How Foveated MLLMs Search Compared to Humans
arXiv:2608. 16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath.
arXiv AI
Sep 2
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
The study investigates whether attention weights in Vision‑Language Models (VLMs) accurately reflect model reasoning for visual inputs. Using causal perturbation analysis, it identifies three distinct processing modes—Faithful‑Sufficient, Faithful‑Distributed, and Non‑Focal—indicating heterogeneous visual attention faithfulness. The research also shows that human‑annotated ground‑truth regions align with model attention in only about 60% of cases, highlighting a systematic divergence between model visual reliance and human intuition across VQA, document, and chart tasks.
arXiv Machine Learning
Jun 15
Gaze Heads: How VLMs Look at What They Describe
arXiv:2606. 14703v1 Announce Type: cross Abstract: How a vision-language model internally solves the task of describing an image is far from obvious.
arXiv AI
Jul 9
Thinking Ahead: Foresight Intelligence in MLLMs and World Model
arXiv:2511. 18735v3 Announce Type: replace-cross Abstract: In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research.
arXiv Computation and Language
Sep 4
Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR
The paper introduces EASE, a method that enhances multimodal reinforcement learning with verifiable rewards (RLVR) by adding visual‑evidence process supervision. EASE transforms annotated evidence regions into smoothed visual‑token targets and uses them to guide attention during RL training, but only on high‑reward trajectories. Experiments on Qwen2.5‑VL‑7B, Qwen3‑VL‑4B, and Qwen3‑VL‑8B show that EASE improves average scores over DAPO by 2.5 to 3.1 points across perception, hallucination, visual math, and multimodal reasoning benchmarks, and diagnostics confirm better alignment of visual attention with annotated evidence.