Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
read the original abstract
Pre-trained vision and language models have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and information-seeking. In this study, we introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge. Using InfoSeek, we analyze various pre-trained visual question answering models and gain insights into their characteristics. Our findings reveal that state-of-the-art pre-trained multi-modal models (e.g., PaLI-X, BLIP2, etc.) face challenges in answering visual information-seeking questions, but fine-tuning on the InfoSeek dataset elicits models to use fine-grained knowledge that was learned during their pre-training. Furthermore, we show that accurate visual entity recognition can be used to improve performance on InfoSeek by retrieving relevant documents, showing a significant space for improvement.
This paper has not been read by Pith yet.
Forward citations
Cited by 17 Pith papers
-
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.
-
WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
WikiCLIP delivers an efficient contrastive baseline for open-domain visual entity recognition that improves accuracy by 16% on OVEN unseen entities and runs nearly 100 times faster than leading generative models.
-
Evaluating the Search Agent in a Parallel World
Mind-ParaWorld creates parallel worlds with atomic facts to evaluate search agents on future scenarios, showing they synthesize evidence well but struggle with collection, coverage, sufficiency judgment, and stopping ...
-
MMSearch-R1: Incentivizing LMMs to Search
MMSearch-R1 uses reinforcement learning to train multimodal models for on-demand multi-turn internet search with image and text tools, outperforming same-size RAG baselines and matching larger ones while cutting searc...
-
Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting
Audit of KB-VQA benchmarks reveals systematic violations of answer derivability, question clarity, and visual disambiguation assumptions, with new repair and multi-entity augmentation protocols producing different mod...
-
Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification
A decoupled training-free IBA framework for KB-VQA selects entities via MLLM candidate choice then ranks evidence with off-the-shelf re-rankers, outperforming coupled fine-tuned baselines on Encyclopedic-VQA and InfoSeek.
-
DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
DR-MMSearchAgent derives batch-wide trajectory advantages and uses differentiated Gaussian rewards to prevent premature collapse in multimodal agents, outperforming MMSearch-R1 by 8.4% on FVQA-test.
-
Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answering
A decision-based agent for KB-VQA learns to dynamically select retrieval or answer actions over multiple steps and achieves state-of-the-art results on InfoSeek and E-VQA after fine-tuning on automatically collected t...
-
R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
R3G improves vision-centric visual question answering by generating reasoning plans to guide two-stage image retrieval and reranking, achieving state-of-the-art results on MRAG-Bench across six MLLM backbones.
-
DeepEyesV2: Toward Agentic Multimodal Model
DeepEyesV2 uses a two-stage cold-start plus reinforcement learning pipeline to produce an agentic multimodal model that adaptively invokes tools and outperforms direct RL on real-world reasoning benchmarks.
-
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent
WebWatcher introduces a vision-language deep research agent trained on synthetic multimodal trajectories and RL that outperforms baselines on VQA benchmarks, along with a new BrowseComp-VL evaluation.
-
Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
-
MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning
MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathe...
-
ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
A sandbox-trained multimodal search agent with process-oriented rewards transfers zero-shot to real Google Search and outperforms prior methods on FVQA, InfoSeek, and MMSearch.
-
SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search
SimpleSearch-VL improves Qwen3-VL multimodal agent baselines by 15.8-16 points on average using 7K total training examples and reaches parity with Gemini-3-Pro on the 30B variant.
-
Delineating Knowledge Boundaries for Honest Large Vision-Language Models
VLMs fine-tuned on a consistency-probed Visual-Idk dataset via SFT and preference optimization raise truthful rate from 57.9% to 67.3% and show internal evidence of genuine boundary recognition.
-
PaLI-X: On Scaling up a Multilingual Vision and Language Model
Scaling a multilingual vision-language model in size and training breadth yields new state-of-the-art results on over 25 benchmarks plus emerging abilities in counting and multilingual detection.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.