C3-Bench supplies a multi-domain dataset and LLM-based evaluation protocol that exposes systematic failures in existing change captioning models outside their training regimes.
Visual haystacks: A vision-centric needle-in-a-haystack benchmark
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to process a large number of visual tokens does not guarantee effective retrieval and reasoning for multi-image question answering (MIQA), especially in real-world applications like photo album searches or satellite imagery analysis. In this work, we first assess the limitations of current benchmarks for long-context LMMs. We address these limitations by introducing a new vision-centric, long-context benchmark, "Visual Haystacks (VHs)". We comprehensively evaluate both open-source and proprietary models on VHs, and demonstrate that these models struggle when reasoning across potentially unrelated images, perform poorly on cross-image reasoning, as well as exhibit biases based on the placement of key information within the context window. Towards a solution, we introduce MIRAGE (Multi-Image Retrieval Augmented Generation), an open-source, lightweight visual-RAG framework that processes up to 10k images on a single 40G A100 GPU -- far surpassing the 1k-image limit of contemporary models. MIRAGE demonstrates up to 13% performance improvement over existing open-source LMMs on VHs, sets a new state-of-the-art on the RetVQA multi-image QA benchmark, and achieves competitive performance on single-image QA with state-of-the-art LMMs. Our dataset, model, and code are available at: https://visual-haystacks.github.io.
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
VisualMem augments text memory with a visual module that resolves identity and durable user facts from images, outperforming prior systems on a new benchmark for explicit and implicit personal visual evidence.
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
A modular 8B agent with episodic visual memory and RL-trained retrieval reaches 91.4% cross-turn image recall over 20 turns, outperforming 32B all-context baselines with ~1.8× lower latency.
Presents Invoice Haystack benchmark for homogeneous document retrieval and VL-RAG hybrid framework achieving 60% Recall@1 and up to 13.5 point gains over prior methods.
Continued pre-training with balanced long-document VQA data extends a 7B LVLM to 128K context, improving long-document VQA by 7.1% and generalizing to 512K without further training.
PulseFocus improves multi-image reasoning in VLMs by interleaving planning and attention-gated focus blocks during chain-of-thought, achieving gains on BLINK and MuirBench.
citing papers explorer
-
C3-Bench: A Context-Aware Change Captioning Benchmark
C3-Bench supplies a multi-domain dataset and LLM-based evaluation protocol that exposes systematic failures in existing change captioning models outside their training regimes.
-
Personal Visual Memory from Explicit and Implicit Evidence
VisualMem augments text memory with a visual module that resolves identity and durable user facts from images, outperforming prior systems on a new benchmark for explicit and implicit personal visual evidence.
-
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
Evidence utility is defined as information gain on the model's output distribution, with ranking by gain on a latent helpfulness variable shown equivalent to answer-space utility under mild assumptions, enabling a training-free surrogate framework that outperforms baselines.
-
Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing
A modular 8B agent with episodic visual memory and RL-trained retrieval reaches 91.4% cross-turn image recall over 20 turns, outperforming 32B all-context baselines with ~1.8× lower latency.
-
Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity
Presents Invoice Haystack benchmark for homogeneous document retrieval and VL-RAG hybrid framework achieving 60% Recall@1 and up to 13.5 point gains over prior methods.
-
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Continued pre-training with balanced long-document VQA data extends a 7B LVLM to 128K context, improving long-document VQA by 7.1% and generalizing to 512K without further training.
-
Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks
PulseFocus improves multi-image reasoning in VLMs by interleaving planning and attention-gated focus blocks during chain-of-thought, achieving gains on BLINK and MuirBench.