ML + Vision Top-6 Agent Survey - ICML 2025 - Page 3 of 4¶
- Venue: International Conference on Machine Learning
- Year: 2025
- Page: 3 / 4
- Papers: 61-90 / 98
Papers
PoisonedEye: Knowledge Poisoning Attack on Retrieval-Augmented Generation based Large Vision-Language Models Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models Paper
Abstract
Exploration is a cornerstone of reinforcement learning (RL). Intrinsic motivation attempts to decouple exploration from external, task-based rewards. However, established approaches to intrinsic motivation that follow general principles such as information gain, often only uncover low-level interactions. In contrast, children's play suggests that they engage in meaningful high-level behavior by imitating or interacting with their caregivers. Recent work has focused on using foundation models to inject these semantic biases into exploration. However, these methods often rely on unrealistic assumptions, such as language-embedded environments or access to high-level actions. We propose SEmaNtically Sensible ExploratIon (SENSEI), a framework to equip model-based RL agents with an intrinsic motivation for semantically meaningful behavior. SENSEI distills a reward signal of interestingness from Vision Language Model (VLM) annotations, enabling an agent to predict these rewards through a world model. Using model-based RL, SENSEI trains an exploration policy that jointly maximizes semantic rewards and uncertainty. We show that in both robotic and video game-like simulations SENSEI discovers a variety of meaningful behaviors from image observations and low-level actions. SENSEI provides a general tool for learning from foundation model feedback, a crucial research direction, as VLMs become more powerful.
Claim
Exploration is a cornerstone of reinforcement learning (RL).
MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces Paper
Abstract
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP). When such autotelic exploration is achieved by LLM agents trained with online RL in high-dimensional and evolving goal spaces, a key challenge for LP prediction is modeling one's own competence, a form of metacognitive monitoring. Traditional approaches either require extensive sampling or rely on brittle expert-defined goal groupings. We introduce MAGELLAN, a metacognitive framework that lets LLM agents learn to predict their competence and LP online. By capturing semantic relationships between goals, MAGELLAN enables sample-efficient LP estimation and dynamic adaptation to evolving goal spaces through generalization. In an interactive learning environment, we show that MAGELLAN improves LP prediction efficiency and goal prioritization, being the only method allowing the agent to fully master a large and evolving goal space. These results demonstrate how augmenting LLM agents with a metacognitive ability for LP predictions can effectively scale curriculum learning to open-ended goal spaces.
Claim
Open-ended learning agents must efficiently prioritize goals in vast possibility spaces, focusing on those that maximize learning progress (LP).
From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs Paper
Abstract
3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-order-of-magnitude gap that severely limits performance. We introduce \(**LIFT-GS**\), a practical distillation technique that overcomes this limitation by using differentiable rendering to bridge 3D and 2D supervision. LIFT-GS predicts 3D Gaussian representations from point clouds and uses them to render predicted language-conditioned 3D masks into 2D views, enabling supervision from 2D foundation models (SAM, CLIP, LLaMA) without requiring any 3D annotations. This render-supervised formulation enables end-to-end training of complete encoder-decoder architectures and is inherently model-agnostic. LIFT-GS achieves state-of-the-art results with \(25.7%\) mAP on open-vocabulary instance segmentation (vs. \(20.2%\) prior SOTA) and consistent \(10-30%\) improvements on referential grounding tasks. Remarkably, pretraining effectively multiplies fine-tuning datasets by 2X, demonstrating strong scaling properties that suggest 3D VLG currently operates in a severely data-scarce regime. Project page: https://liftgs.github.io
Claim
3D vision-language grounding faces a fundamental data bottleneck: while 2D models train on billions of images, 3D models have access to only thousands of labeled scenes--a six-order-of-magnitude gap that severely limits performance.
From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection Paper
Abstract
Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks. Prior research highlights the crucial role of visual augmentation techniques, like random cropping, in alignment with fine-grained class descriptions generated by large language models (LLMs), significantly enhancing zero-shot performance by incorporating multi-view information. However, the inherent randomness of these augmentations can inevitably introduce background artifacts and cause models to overly focus on local details, compromising global semantic understanding. To address these issues, we propose an Attention-Based Selection (ABS) method from local details to global context, which applies attention-guided cropping in both raw images and feature space, supplement global semantic information through strategic feature selection. Additionally, we introduce a soft matching technique to effectively filter LLM descriptions for better alignment. ABS achieves state-of-the-art performance on out-of-distribution generalization and zero-shot classification tasks. Notably, ABS is training-free and even rivals few-shot and test-time adaptation methods. Our code is available at \href{https://github.com/BIT-DA/ABS}{\textcolor{darkgreen}{https://github.com/BIT-DA/ABS}}.
Claim
Pretrained vision-language models (VLMs), e.g., CLIP, demonstrate impressive zero-shot capabilities on downstream tasks.
An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability Paper
Abstract
The advancements in Multimodal Large Language Models (MLLMs) have enabled various multimodal tasks to be addressed under a zero-shot paradigm. This paradigm sidesteps the cost of model fine-tuning, emerging as a dominant trend in practical application. Nevertheless, Multimodal Sentiment Analysis (MSA), a pivotal challenge in the quest for general artificial intelligence, fails to accommodate this convenience. The zero-shot paradigm exhibits undesirable performance on MSA, casting doubt on whether MLLMs can perceive sentiments as competent as supervised models. By extending the zero-shot paradigm to In-Context Learning (ICL) and conducting an in-depth study on configuring demonstrations, we validate that MLLMs indeed possess such capability. Specifically, three key factors that cover demonstrations' retrieval, presentation, and distribution are comprehensively investigated and optimized. A sentimental predictive bias inherent in MLLMs is also discovered and later effectively counteracted. By complementing each other, the devised strategies for three factors result in average accuracy improvements of 15.9% on six MSA datasets against the zero-shot paradigm and 11.2% against the random ICL baseline.
Claim
The advancements in Multimodal Large Language Models (MLLMs) have enabled various multimodal tasks to be addressed under a zero-shot paradigm.
Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger Paper
Abstract
Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks through multimodal Retrieval-Augmented Generation (RAG). However, existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge. To address these issues, in this study, we propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method. Specifically, we introduce a self-consistent evaluation mechanism to enrich the knowledge base with intrinsic reasoning patterns. We further propose a Monte Carlo Tree Search with Heuristic Rewards (MCTS-HR) to prioritize the most relevant examples. This ensures that LVLMs can leverage high-quality contextual reasoning for better and more consistent responses. Extensive experiments demonstrate that our framework achieves state-of-the-art performance on multiple VQA datasets, significantly outperforming In-Context Learning (ICL) and Vanilla-RAG methods. It highlights the effectiveness of our knowledge base and re-ranking method in improving LVLMs. Our code is available at https://github.com/yannqi/RCTS-RAG.
Claim
Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks through multimodal Retrieval-Augmented Generation (RAG).
HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming Paper
Abstract
Two-stage Stochastic Programming (2SP) is a standard framework for modeling decision-making problems under uncertainty. While numerous methods exist, solving such problems with many scenarios remains challenging. Selecting representative scenarios is a practical method for accelerating solutions. However, current approaches typically rely on clustering or Monte Carlo sampling, failing to integrate scenario information deeply and overlooking the significant impact of the scenario order on solving time. To address these issues, we develop HGCN2SP, a novel model with a hierarchical graph designed for 2SP problems, encoding each scenario and modeling their relationships hierarchically. The model is trained in a reinforcement learning paradigm to utilize the feedback of the solver. The policy network is equipped with a hierarchical graph convolutional network for feature encoding and an attention-based decoder for scenario selection in proper order. Evaluation of two classic 2SP problems demonstrates that HGCN2SP provides high-quality decisions in a short computational time. Furthermore, HGCN2SP exhibits remarkable generalization capabilities in handling large-scale instances, even with a substantial number of variables or scenarios that were unseen during the training phase.
Claim
Two-stage Stochastic Programming (2SP) is a standard framework for modeling decision-making problems under uncertainty.
Vision-Language Model Selection and Reuse for Downstream Adaptation Paper
Abstract
Pre-trained Vision-Language Models (VLMs) are becoming increasingly popular across various visual tasks, and several open-sourced VLM variants have been released. However, selecting the best-performing pre-trained VLM for a specific downstream task is challenging since no single VLM can achieve promising performance on all downstream tasks, and evaluating all available VLMs is impossible due to time and data limitations. To address this problem, this paper proposes a novel paradigm to select and reuse VLM for downstream tasks, called Model Label Learning (MLL). The proposal contains three key modules: model labeling, which assigns labels to each VLM to describe their specialty and utility; model selection, which matches the requirements of the target task with model labels; and model reuse, which applies selected VLMs to the target task in an ensemble manner. The proposal is highly computationally efficient and growable since the model labeling process is completed target task independent and the ability could grow with the number of candidate VLMs. We also introduce a new benchmark for evaluating VLM selection methods, including 49 VLMs and 17 target task datasets. Experimental results clearly demonstrate the effectiveness of the proposed method for selecting and reusing VLMs.
Claim
Pre-trained Vision-Language Models (VLMs) are becoming increasingly popular across various visual tasks, and several open-sourced VLM variants have been released.
CoMemo: LVLMs Need Image Context with Image Memory Paper
Abstract
Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm. However, inherited LLM architectural designs introduce suboptimal characteristics for multimodal processing. First, LVLMs exhibit a bimodal distribution in attention allocation, leading to the progressive neglect of middle visual content as context expands. Second, conventional positional encoding schemes fail to preserve vital 2D structural relationships when processing dynamic high-resolution images. To address these limitations, we propose CoMemo - a dual-path architecture that combines a Context image path with an image Memory path for visual processing, effectively alleviating visual information neglect. Additionally, we introduce RoPE-DHR, a novel positional encoding mechanism that employs thumbnail-based positional aggregation to maintain 2D spatial awareness while mitigating remote decay in extended sequences. Evaluations across seven benchmarks,including long-context comprehension, multi-image reasoning, and visual question answering, demonstrate CoMemo's superior performance compared to conventional LVLM architectures. Project page is available at https://lalbj.github.io/projects/CoMemo/.
Claim
Recent advancements in Large Vision-Language Models built upon Large Language Models have established aligning visual features with LLM representations as the dominant paradigm.
From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models Paper
Abstract
As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interpretative exploration of their internal mechanisms. In response, this study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of ToM in multimodal large language models (MLLMs). Specifically, we first construct a multimodal ToM test dataset, GridToM, which incorporates diverse belief testing tasks and perceptual information from multiple perspectives. Next, our analysis shows that attention heads in multimodal large models can distinguish cognitive information across perspectives, providing evidence of ToM capabilities. Furthermore, we present a lightweight, training-free approach that significantly enhances the model's exhibited ToM by adjusting in the direction of the attention head.
Claim
As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks.
World Model Implanting for Test-time Adaptation of Embodied Agents Paper
Abstract
In embodied AI, a persistent challenge is enabling agents to robustly adapt to novel domains without requiring extensive data collection or retraining. To address this, we present a world model implanting framework (WorMI) that combines the reasoning capabilities of large language models (LLMs) with independently learned, domain-specific world models through test-time composition. By allowing seamless implantation and removal of the world models, the embodied agent's policy achieves and maintains cross-domain adaptability. In the WorMI framework, we employ a prototype-based world model retrieval approach, utilizing efficient trajectory-based abstract representation matching, to incorporate relevant models into test-time composition. We also develop a world-wise compound attention method that not only integrates the knowledge from the retrieved world models but also aligns their intermediate representations with the reasoning model's representation within the agent's policy. This framework design effectively fuses domain-specific knowledge from multiple world models, ensuring robust adaptation to unseen domains. We evaluate our WorMI on the VirtualHome and ALFWorld benchmarks, demonstrating superior zero-shot and few-shot performance compared to several LLM-based approaches across a range of unseen domains. These results highlight the frameworks potential for scalable, real-world deployment in embodied agent scenarios where adaptability and data efficiency are essential.
Claim
In embodied AI, a persistent challenge is enabling agents to robustly adapt to novel domains without requiring extensive data collection or retraining.
Primitive Vision: Improving Diagram Understanding in MLLMs Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models Paper
Abstract
Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks, allowing us to systematically evaluate performance across cognitive domains under a consistent environment. We fine-tune models on ground truth data for intuitive physics and causal reasoning and find that this improves model performance in the respective fine-tuning domain. Furthermore, it can improve model alignment with human behavior. However, we find that task-specific fine-tuning does not contribute to robust human-like generalization to data with other visual characteristics or to tasks in other cognitive domains.
Claim
Pre-trained vision language models still fall short of human visual cognition.
Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Textural or Textual: How Vision-Language Models Read Text in Images Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Learning to Generate Projections for Reducing Dimensionality of Heterogeneous Linear Programming Problems Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
DIS-CO: Discovering Copyrighted Content in VLMs Training Data Paper
Abstract
How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data? Motivated by the hypothesis that a VLM is able to recognize images from its training corpus, we propose DIS-CO, a novel approach to infer the inclusion of copyrighted content during the model's development. By repeatedly querying a VLM with specific frames from targeted copyrighted material, DIS-CO extracts the content's identity through free-form text completions. To assess its effectiveness, we introduce MovieTection, a benchmark comprising 14,000 frames paired with detailed captions, drawn from films released both before and after a model's training cutoff. Our results show that DIS-CO significantly improves detection performance, nearly doubling the average AUC of the best prior method on models with logits available. Our findings also highlight a broader concern: all tested models appear to have been exposed to some extent to copyrighted content. Our code and data are available at https://github.com/avduarte333/DIS-CO
Claim
How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data? Motivated by the hypothesis that a VLM is able to recognize images from its training corpus, we propose DIS-CO, a novel approach to infer the inclusion of copyrighted content during the model's development.
Pareto-Optimal Fronts for Benchmarking Symbolic Regression Algorithms Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Do Vision-Language Models Really Understand Visual Language? Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
DS-VLM: Diffusion Supervision Vision Language Model Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Diffusion Instruction Tuning Paper
Abstract
We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion. Specifically, Lavender aligns the text-vision attention in the VLM transformer with the equivalent used by Stable Diffusion during SFT, instead of adapting separate encoders. This alignment enriches the model's visual understanding and significantly boosts performance across in- and out-of-distribution tasks. Lavender requires just 0.13 million training examples, 2.5% of typical large-scale SFT datasets, and fine-tunes on standard hardware (8 GPUs) in a single day. It consistently improves state-of-the-art open-source multimodal LLMs (e.g., Llama-3.2-11B, MiniCPM-Llama3-v2.5), achieving up to 30% gains and a 68% boost on challenging out-of-distribution medical QA tasks. By efficiently transferring the visual expertise of image generators with minimal supervision, Lavender offers a scalable solution for more accurate vision-language systems. All code, training data, and models will be shared at https://astrazeneca.github.io/vlm/.
Claim
We introduce Lavender, a simple supervised fine-tuning (SFT) method that boosts the performance of advanced vision-language models (VLMs) by leveraging state-of-the-art image generation models such as Stable Diffusion.
LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Paper
Abstract
Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a large number of visual tokens in cross-attention layers leads to high memory demands and often necessitates distributed computation across multiple GPUs. Existing distributed attention mechanisms face significant communication overheads, making cross-attention layers a critical bottleneck for efficient training and inference of MLLMs. To address this, we propose LV-XAttn, a distributed, exact cross-attention mechanism with minimal communication overhead. We observe that in applications involving large visual inputs, the size of the query block is typically much smaller than that of the key-value blocks. Thus, in LV-XAttn we keep the large key-value blocks locally on each GPU and exchange smaller query blocks across GPUs. We also introduce an efficient activation recomputation technique to support longer visual context. We theoretically analyze the communication benefits of LV-XAttn and show that it can achieve speedups for a wide range of models. Our evaluations with Llama 3-V, mPLUG-Owl3 and OpenFlamingo models find that LV-XAttn achieves up to 10.62\(\times\) end-to-end speedup compared to existing approaches.
Claim
Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone.
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models Paper
Abstract
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations in visual form, a basic ability of human reasoning. To address this challenge, we introduce the Visual Graph Arena (VGA), a dataset featuring six graph-based tasks designed to evaluate and improve AI systems' capacity for visual abstraction. VGA uses diverse graph layouts (e.g., Kamada-Kawai vs. planar) to test reasoning independent of visual form. Experiments with state-of-the-art vision models and multimodal LLMs reveal a striking divide: humans achieved near-perfect accuracy across tasks, while models totally failed on isomorphism detection and showed limited success in path/cycle tasks. We further identify behavioral anomalies suggesting pseudo-intelligent pattern matching rather than genuine understanding. These findings underscore fundamental limitations in current AI models for visual understanding. By isolating the challenge of representation-invariant reasoning, the VGA provides a framework to drive progress toward human-like conceptualization in AI visual models. The Visual Graph Arena is available at: \href{https://vga.csail.mit.edu/}{vga.csail.mit.edu}
Claim
Recent advancements in multimodal large language models have driven breakthroughs in visual question answering.