large-vision-language-models

Tag

Cards List
#large-vision-language-models

Soft Spatial Reasoning

Hugging Face Daily Papers ↗ · 2026-09-30 Cached

The paper proposes Soft Spatial Reasoning, a post-training framework that introduces adaptive "soft thinking" for spatial tasks in Large Vision-Language Models, where intermediate reasoning steps mix token embeddings instead of committing to a single discrete token. An AdaptSoft controller dynamically adjusts softness based on hidden state and predictive uncertainty, outperforming hard and fixed-soft CoT baselines on spatial benchmarks.

0 favorites 0 likes
#large-vision-language-models

TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams

arXiv cs.CL ↗ · 2026-09-15 Cached

This paper introduces TestHallVQA, a multi-image VQA benchmark for evaluating Large Vision-Language Models' document-level reasoning under redundant contexts, and proposes a new metric F1-R2 to quantify computational reasoning and robustness.

0 favorites 0 likes
#large-vision-language-models

UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models

Hugging Face Daily Papers ↗ · 2026-07-25 Cached

UltraViT is a latency-optimized vision encoder for large vision-language models, designed for on-device deployment with a pyramidal architecture and a two-stage generative pre-training strategy, achieving state-of-the-art performance at 1.7x speed.

0 favorites 0 likes
#large-vision-language-models

FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models

arXiv cs.AI ↗ · 2026-06-30 Cached

This paper proposes FADE, a training-free method that mitigates hallucinations in Large Vision-Language Models by attenuating FFN outputs at critical layers to reduce language-prior dominance, demonstrating effectiveness across multiple benchmarks.

0 favorites 0 likes
#large-vision-language-models

MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation

arXiv cs.CL ↗ · 2026-06-17 Cached

Introduces MODE-RAG, a multi-agent system using Variational Free Energy and Monte Carlo Tree Search to dynamically gate interventions for mitigating hallucinations in Multimodal Retrieval-Augmented Generation systems, along with the ModeVent evaluation dataset.

0 favorites 0 likes
#large-vision-language-models

CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment

arXiv cs.CL ↗ · 2026-06-15 Cached

This paper analyzes the thinking-answer inconsistency in multimodal reinforcement learning with verifiable rewards (RLVR) for large vision-language models and proposes CORA, a method that introduces a consistency reward model and hybrid reward advantage splitting to improve faithfulness and task performance.

0 favorites 0 likes
#large-vision-language-models

VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation

Hugging Face Daily Papers ↗ · 2026-05-23 Cached

VaaWIT is an end-to-end framework enhancing Large Vision-Language Models for multilingual Web image translation via dual-stream attention and visual-aware adapters, outperforming SOTA baselines.

0 favorites 0 likes
#large-vision-language-models

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

Hugging Face Daily Papers ↗ · 2026-05-15 Cached

VideoSeeker introduces a paradigm for instance-level video understanding that integrates agentic reasoning with visual prompts, achieving superior performance through automated data synthesis and reinforcement learning, outperforming GPT-4o and Gemini-2.5-Pro.

0 favorites 0 likes
#large-vision-language-models

Built Environment Reasoning from Remote Sensing Imagery Using Large Vision--Language Models

arXiv cs.CL ↗ · 2026-05-12 Cached

This paper investigates using large vision-language models for built environment reasoning tasks, such as design suggestions and risk identification, leveraging remote sensing imagery. It evaluates models like InternVL and Qwen, highlighting their potential for supporting smart city decision-making and quantitative reasoning.

0 favorites 0 likes
← Back to home

Submit Feedback