arXiv Computation and Language
GUIDE: Guiding Internal Evidence with Language Instructions
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Aug 6
Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models
arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.
arXiv AI
4d ago
Multimodal In-Context Learning with Explicit Rule Induction
arXiv:2610.41754v1 Announce Type: new Abstract: A central challenge in multimodal in-context learning (MICL) arises from tasks that are ill-defined without context and require uncovering the underlyi...
arXiv AI
Oct 12
The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs
The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.
arXiv AI
Jun 16
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
arXiv:2602. 12279v2 Announce Type: replace-cross Abstract: Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs.
arXiv Computer Vision
Oct 9
Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning
The paper introduces ViMoD, a lightweight framework that dynamically manages visual memory for multimodal large language models. ViMoD uses Deformable Aggregation of Region-wise Tokens (DART) to create content‑adaptive coarse representations linked to recoverable fine tokens, and Temporal Routing for Adaptive Contextual Evidence (TRACE) to anticipate and adjust evidence needs during reasoning. On the Qwen3‑VL‑4B model, ViMoD achieves superior performance across eight reasoning benchmarks with only a 20% visual token budget and minimal additional parameters.
arXiv AI
Jul 7
Attending to Multimodal Generation One Token at a Time
arXiv:2607. 03738v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context.