# Research Papers — 2025-10 · bundle page 55 of 217 > Full-text markdown of papers #2701–2750 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/55 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/54.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/56.md) ### Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People Authors: Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.20886v1 Many high-stakes applications of AI require forming data-driven hypotheses and making targeted guesses; e.g., in scientific and diagnostic settings. Given limited resources, to what extent do agents based on language models (LMs) act rationally? We develop methods to benchmark and enhance agentic information-seeking, drawing on insights from human behavior. First, we introduce a strategic decision-oriented dialogue task called Collaborative Battleship, in which a partially-informed Captain must balance exploration (asking questions) and action (taking shots), while a fully-informed Spotter must provide accurate answers under an information bottleneck. Compared to human players (N=42), we find that LM agents struggle to ground answers in context, generate informative questions, and select high-value actions. Next, to address these gaps, we develop novel Monte Carlo inference strategies for LMs based on principles from Bayesian Experimental Design (BED). For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling). Combined, these components yield sharper targeting (+0.303-0.374 F1), and enable weaker LMs, such as Llama-4-Scout, to outperform both humans (8% -> 82% win rate) and frontier models (0% -> 67% win rate vs. GPT-5) at ~1% of GPT-5's cost. We replicate these findings on Guess Who? where our methods significantly boost accuracy (+28.3-42.4 p.p.), demonstrating their general applicability for building rational information-seeking agents. --- ### ROPES: Robotic Pose Estimation via Score-Based Causal Representation Learning Authors: Pranamya Kulkarni, Puranjay Datta, Burak Varıcı, Emre Acartürk, Karthikeyan Shanmugam, Ali Tajer Published: 2025-10-23 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2510.20884v1 Causal representation learning (CRL) has emerged as a powerful unsupervised framework that (i) disentangles the latent generative factors underlying high-dimensional data, and (ii) learns the cause-and-effect interactions among the disentangled variables. Despite extensive recent advances in identifiability and some practical progress, a substantial gap remains between theory and real-world practice. This paper takes a step toward closing that gap by bringing CRL to robotics, a domain that has motivated CRL. Specifically, this paper addresses the well-defined robot pose estimation -- the recovery of position and orientation from raw images -- by introducing Robotic Pose Estimation via Score-Based CRL (ROPES). Being an unsupervised framework, ROPES embodies the essence of interventional CRL by identifying those generative factors that are actuated: images are generated by intrinsic and extrinsic latent factors (e.g., joint angles, arm/limb geometry, lighting, background, and camera configuration) and the objective is to disentangle and recover the controllable latent variables, i.e., those that can be directly manipulated (intervened upon) through actuation. Interventional CRL theory shows that variables that undergo variations via interventions can be identified. In robotics, such interventions arise naturally by commanding actuators of various joints and recording images under varied controls. Empirical evaluations in semi-synthetic manipulator experiments demonstrate that ROPES successfully disentangles latent generative factors with high fidelity with respect to the ground truth. Crucially, this is achieved by leveraging only distributional changes, without using any labeled data. The paper also includes a comparison with a baseline based on a recently proposed semi-supervised framework. This paper concludes by positioning robot pose estimation as a near-practical testbed for CRL. --- ### Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization Authors: Antônio H. Ribeiro, David Vävinggren, Dave Zachariah, Thomas B. Schön, Francis Bach Published: 2025-10-23 Categories: stat.ML, cs.CR, cs.LG, math.OC arXiv: https://arxiv.org/abs/2510.20883v1 Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods rely on computationally expensive min-max problems that limit their application in practice. We propose a novel formulation of adversarial training in reproducing kernel Hilbert spaces, shifting from input to feature-space perturbations. This reformulation enables the exact solution of inner maximization and efficient optimization. It also provides a regularized estimator that naturally adapts to the noise level and the smoothness of the underlying function. We establish conditions under which the feature-perturbed formulation is a relaxation of the original problem and propose an efficient optimization algorithm based on iterative kernel ridge regression. We provide generalization bounds that help to understand the properties of the method. We also extend the formulation to multiple kernel learning. Empirical evaluation shows good performance in both clean and adversarial settings. --- ### HA-RAG: Hotness-Aware RAG Acceleration via Mixed Precision and Data Placement Authors: Danying Ge, Jianhua Gao, Yixue Yang, Weixing Ji Published: 2025-10-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.20878v1 Retrieval-Augmented Generation (RAG) improves model output accuracy by leveraging external knowledge bases, serving as an effective solution to address hallucination issues and knowledge-update delays in Large Language Models (LLMs). However, the introduction of external knowledge bases presents RAG with challenges in long-context processing, significantly increasing memory consumption and inference latency. Existing research accelerates inference by precomputing Key and Value (KV) of the knowledge base and loading them on-demand during inference. Based on the access frequency of different KV chunks within the external knowledge base, this paper proposes a hotness-aware RAG (HA-RAG) inference optimization system. First, leveraging the numerical distribution of KV chunks, we introduce a hotness-aware mixed-precision compressing and loading method to reduce disk I/O and memory access overhead. Second, we design a hotness-aware data placement strategy that prioritizes storing frequently accessed KV chunks in high-speed memory to improve data access efficiency. Experimental results demonstrate that, compared with TurboRAG, the proposed HA-RAG achieves an average speedup of 2.10x and maximum speedup of 10.49x in Time-To-First-Token (TTFT) with negligible accuracy loss. --- ### Multimodal Negative Learning Authors: Baoquan Gong, Xiyuan Gao, Pengfei Zhu, Qinghua Hu, Bing Cao Published: 2025-10-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.20877v1 Multimodal learning systems often encounter challenges related to modality imbalance, where a dominant modality may overshadow others, thereby hindering the learning of weak modalities. Conventional approaches often force weak modalities to align with dominant ones in "Learning to be (the same)" (Positive Learning), which risks suppressing the unique information inherent in the weak modalities. To address this challenge, we offer a new learning paradigm: "Learning Not to be" (Negative Learning). Instead of enhancing weak modalities' target-class predictions, the dominant modalities dynamically guide the weak modality to suppress non-target classes. This stabilizes the decision space and preserves modality-specific information, allowing weak modalities to preserve unique information without being over-aligned. We proceed to reveal multimodal learning from a robustness perspective and theoretically derive the Multimodal Negative Learning (MNL) framework, which introduces a dynamic guidance mechanism tailored for negative learning. Our method provably tightens the robustness lower bound of multimodal learning by increasing the Unimodal Confidence Margin (UCoM) and reduces the empirical error of weak modalities, particularly under noisy and imbalanced scenarios. Extensive experiments across multiple benchmarks demonstrate the effectiveness and generalizability of our approach against competing methods. The code will be available at https://github.com/BaoquanGong/Multimodal-Negative-Learning.git. --- ### CC-GRMAS: A Multi-Agent Graph Neural System for Spatiotemporal Landslide Risk Assessment in High Mountain Asia Authors: Mihir Panchal, Ying-Jung Chen, Surya Parkash Published: 2025-10-23 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.20875v1 Landslides are a growing climate induced hazard with severe environmental and human consequences, particularly in high mountain Asia. Despite increasing access to satellite and temporal datasets, timely detection and disaster response remain underdeveloped and fragmented. This work introduces CC-GRMAS, a framework leveraging a series of satellite observations and environmental signals to enhance the accuracy of landslide forecasting. The system is structured around three interlinked agents Prediction, Planning, and Execution, which collaboratively enable real time situational awareness, response planning, and intervention. By incorporating local environmental factors and operationalizing multi agent coordination, this approach offers a scalable and proactive solution for climate resilient disaster preparedness across vulnerable mountainous terrains. --- ### MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions Authors: Lam Ngo, Huong Ha, Jeffrey Chan, Hongyu Zhang Published: 2025-10-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.20872v1 Bayesian Optimization (BO) is a powerful tool for optimizing expensive black-box objective functions. While extensive research has been conducted on the single-objective optimization problem, the multi-objective optimization problem remains challenging. In this paper, we propose MOBO-OSD, a multi-objective Bayesian Optimization algorithm designed to generate a diverse set of Pareto optimal solutions by solving multiple constrained optimization problems, referred to as MOBO-OSD subproblems, along orthogonal search directions (OSDs) defined with respect to an approximated convex hull of individual objective minima. By employing a well-distributed set of OSDs, MOBO-OSD ensures broad coverage of the objective space, enhancing both solution diversity and hypervolume performance. To further improve the density of the set of Pareto optimal candidate solutions without requiring an excessive number of subproblems, we leverage a Pareto Front Estimation technique to generate additional solutions in the neighborhood of existing solutions. Additionally, MOBO-OSD supports batch optimization, enabling parallel function evaluations to accelerate the optimization process when resources are available. Through extensive experiments and analysis on a variety of synthetic and real-world benchmark functions with two to six objectives, we demonstrate that MOBO-OSD consistently outperforms the state-of-the-art algorithms. Our code implementation can be found at https://github.com/LamNgo1/mobo-osd. --- ### Exponential Convergence Guarantees for Iterative Markovian Fitting Authors: Marta Gentiloni Silveri, Giovanni Conforti, Alain Durmus Published: 2025-10-23 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2510.20871v1 The Schrödinger Bridge (SB) problem has become a fundamental tool in computational optimal transport and generative modeling. To address this problem, ideal methods such as Iterative Proportional Fitting and Iterative Markovian Fitting (IMF) have been proposed-alongside practical approximations like Diffusion Schrödinger Bridge and its Matching (DSBM) variant. While previous work have established asymptotic convergence guarantees for IMF, a quantitative, non-asymptotic understanding remains unknown. In this paper, we provide the first non-asymptotic exponential convergence guarantees for IMF under mild structural assumptions on the reference measure and marginal distributions, assuming a sufficiently large time horizon. Our results encompass two key regimes: one where the marginals are log-concave, and another where they are weakly log-concave. The analysis relies on new contraction results for the Markovian projection operator and paves the way to theoretical guarantees for DSBM. --- ### Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning Authors: Zan Li, Rui Fan Published: 2025-10-23 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2510.20868v1 Financial time series forecasting faces a fundamental challenge: predicting optimal asset allocations requires understanding regime-dependent correlation structures that transform during crisis periods. Existing graph-based spatio-temporal learning approaches rely on predetermined graph topologies--correlation thresholds, sector classifications--that fail to adapt when market dynamics shift across different crisis mechanisms: credit contagion, pandemic shocks, or inflation-driven selloffs. We present CRISP (Crisis-Resilient Investment through Spatio-temporal Patterns), a graph-based spatio-temporal learning framework that encodes spatial relationships via Graph Convolutional Networks and temporal dynamics via BiLSTM with self-attention, then learns sparse structures through multi-head Graph Attention Networks. Unlike fixed-topology methods, CRISP discovers which asset relationships matter through attention mechanisms, filtering 92.5% of connections as noise while preserving crisis-relevant dependencies for accurate regime-specific predictions. Trained on 2005--2021 data encompassing credit and pandemic crises, CRISP demonstrates robust generalization to 2022--2024 inflation-driven markets--a fundamentally different regime--by accurately forecasting regime-appropriate correlation structures. This enables adaptive portfolio allocation that maintains profitability during downturns, achieving Sharpe ratio 3.76: 707% improvement over equal-weight baselines and 94% improvement over static graph methods. Learned attention weights provide interpretable regime detection, with defensive cluster attention strengthening 49% during crises versus 31% market-wide--emergent behavior from learning to forecast rather than imposing assumptions. --- ### Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards Authors: Jiajun Fan, Roger Ren, Jingyuan Li, Rahul Pandey, Prashanth Gurunath Shivakumar, Ivan Bulyko, Ankur Gandhe, Ge Liu, Yile Gu Published: 2025-10-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.20867v1 The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where longer reasoning chains yield progressively worse results. We demonstrate that this stems not from fundamental limitations of reasoning itself, but from inadequate training: models without proper guidance for the reasoning process produce hallucinatory, inconsistent reasoning that accumulates errors over longer chains. To address these challenges, we introduce CESAR (Consistent, Effective, and Scalable Audio Reasoners), shifting from outcome verification to rewarding the reasoning process. Our online reinforcement learning framework employs Group Relative Policy Optimization with a multi-faceted reward suite that incentivizes not only correctness and format but also consistency, structured analytical patterns, causal reasoning, domain-knowledge integration, and calibrated reasoning depth. CESAR resolves test-time inverse scaling, transforming reasoning from detriments into gains while revealing model-specific ``reasoning sweet spots", where performance peaks during test-time scaling. We achieve state-of-the-art results on MMAU Test-mini, substantially outperforming Gemini 2.5 Pro and GPT-4o Audio, and near-human-level performance on MMSU reasoning tasks. Through AI-as-judge evaluations and qualitative comparisons, we provide both quantitative and qualitative validation of our improved reasoning quality. Importantly, enhanced reasoning creates synergistic effects, simultaneously improving multimodal reasoning and perception capabilities. Overall, CESAR establishes a principled method for developing robust and scalable reasoning in Audio LLMs. --- ### Eye-Tracking as a Tool to Quantify the Effects of CAD Display on Radiologists' Interpretation of Chest Radiographs Authors: Daisuke Matsumoto, Tomohiro Kikuchi, Yusuke Takagi, Soichiro Kojima, Ryoma Kobayashi, Daiju Ueda, Kohei Yamamoto, Sho Kawabe, Harushi Mori Published: 2025-10-23 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2510.20864v1 Rationale and Objectives: Computer-aided detection systems for chest radiographs are widely used, and concurrent reader displays, such as bounding-box (BB) highlights, may influence the reading process. This pilot study used eye tracking to conduct a preliminary experiment to quantify which aspects of visual search were affected. Materials and Methods: We sampled 180 chest radiographs from the VinDR-CXR dataset: 120 with solitary pulmonary nodules or masses and 60 without. The BBs were configured to yield an overall display sensitivity and specificity of 80%. Three radiologists (with 11, 5, and 1 years of experience, respectively) interpreted each case twice - once with BBs visible and once without - after a washout of >= 2 weeks. Eye movements were recorded using an EyeTech VT3 Mini. Metrics included interpretation time, time to first fixation on the lesion, lesion dwell time, total gaze-path length, and lung-field coverage ratio. Outcomes were modeled using a linear mixed model, with reading condition as a fixed effect and case and reader as random intercepts. The primary analysis was restricted to true positives (n=96). Results: Concurrent BB display prolonged interpretation time by 4.9 s (p<0.001) and increased lesion dwell time by 1.3 s (p<0.001). Total gaze-path length increased by 2,076 pixels (p<0.001), and lung-field coverage ratio increased by 10.5% (p<0.001). Time to first fixation on the lesion was reduced by 1.3 s (p<0.001). Conclusion: Eye tracking captured measurable alterations in search behavior associated with concurrent BB displays during chest radiograph interpretation. These findings support the feasibility of this approach and highlight the need for larger studies to confirm effects and explore implications across modalities and clinical contexts. --- ### HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives Authors: Yihao Meng, Hao Ouyang, Yue Yu, Qiuyu Wang, Wen Wang, Ka Leong Cheng, Hanlin Wang, Yixuan Li, Cheng Chen, Yanhong Zeng, Yujun Shen, Huamin Qu Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20822v1 State-of-the-art text-to-video models excel at generating isolated clips but fall short of creating the coherent, multi-shot narratives, which are the essence of storytelling. We bridge this "narrative gap" with HoloCine, a model that generates entire scenes holistically to ensure global consistency from the first shot to the last. Our architecture achieves precise directorial control through a Window Cross-Attention mechanism that localizes text prompts to specific shots, while a Sparse Inter-Shot Self-Attention pattern (dense within shots but sparse between them) ensures the efficiency required for minute-scale generation. Beyond setting a new state-of-the-art in narrative coherence, HoloCine develops remarkable emergent abilities: a persistent memory for characters and scenes, and an intuitive grasp of cinematic techniques. Our work marks a pivotal shift from clip synthesis towards automated filmmaking, making end-to-end cinematic creation a tangible future. Our code is available at: https://holo-cine.github.io/. --- ### CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas Authors: Gordon Guocheng Qian, Ruihang Zhang, Tsai-Shien Chen, Yusuf Dalva, Anujraaj Argo Goyal, Willi Menapace, Ivan Skorokhodov, Meng Dong, Arpit Sahni, Daniil Ostashev, Ju Hu, Mukesh Singhal et al. Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20820v4 Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer --- ### LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas Authors: Guocheng Gordon Qian, Ruihang Zhang, Tsai-Shien Chen, Yusuf Dalva, Anujraaj Argo Goyal, Willi Menapace, Ivan Skorokhodov, Meng Dong, Arpit Sahni, Daniil Ostashev, Ju Hu, Sergey Tulyakov et al. Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20820v2 Despite their impressive visual fidelity, existing personalized generative models lack interactive control over spatial composition and scale poorly to multiple subjects. To address these limitations, we present LayerComposer, an interactive framework for personalized, multi-subject text-to-image generation. Our approach introduces two main contributions: (1) a layered canvas, a novel representation in which each subject is placed on a distinct layer, enabling occlusion-free composition; and (2) a locking mechanism that preserves selected layers with high fidelity while allowing the remaining layers to adapt flexibly to the surrounding context. Similar to professional image-editing software, the proposed layered canvas allows users to place, resize, or lock input subjects through intuitive layer manipulation. Our versatile locking mechanism requires no architectural changes, relying instead on inherent positional embeddings combined with a new complementary data sampling strategy. Extensive experiments demonstrate that LayerComposer achieves superior spatial control and identity preservation compared to the state-of-the-art methods in multi-subject personalized image generation. --- ### LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas Authors: Guocheng Gordon Qian, Ruihang Zhang, Tsai-Shien Chen, Yusuf Dalva, Anujraaj Argo Goyal, Willi Menapace, Ivan Skorokhodov, Meng Dong, Arpit Sahni, Daniil Ostashev, Ju Hu, Sergey Tulyakov et al. Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20820v1 Despite their impressive visual fidelity, existing personalized generative models lack interactive control over spatial composition and scale poorly to multiple subjects. To address these limitations, we present LayerComposer, an interactive framework for personalized, multi-subject text-to-image generation. Our approach introduces two main contributions: (1) a layered canvas, a novel representation in which each subject is placed on a distinct layer, enabling occlusion-free composition; and (2) a locking mechanism that preserves selected layers with high fidelity while allowing the remaining layers to adapt flexibly to the surrounding context. Similar to professional image-editing software, the proposed layered canvas allows users to place, resize, or lock input subjects through intuitive layer manipulation. Our versatile locking mechanism requires no architectural changes, relying instead on inherent positional embeddings combined with a new complementary data sampling strategy. Extensive experiments demonstrate that LayerComposer achieves superior spatial control and identity preservation compared to the state-of-the-art methods in multi-subject personalized image generation. --- ### Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge Authors: Nimrod Berman, Omkar Joglekar, Eitan Kosman, Dotan Di Castro, Omri Azencot Published: 2025-10-23 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20819v2 Recent advances in generative modeling have positioned diffusion models as state-of-the-art tools for sampling from complex data distributions. While these models have shown remarkable success across single-modality domains such as images and audio, extending their capabilities to Modality Translation (MT), translating information across different sensory modalities, remains an open challenge. Existing approaches often rely on restrictive assumptions, including shared dimensionality, Gaussian source priors, and modality-specific architectures, which limit their generality and theoretical grounding. In this work, we propose the Latent Denoising Diffusion Bridge Model (LDDBM), a general-purpose framework for modality translation based on a latent-variable extension of Denoising Diffusion Bridge Models. By operating in a shared latent space, our method learns a bridge between arbitrary modalities without requiring aligned dimensions. We introduce a contrastive alignment loss to enforce semantic consistency between paired samples and design a domain-agnostic encoder-decoder architecture tailored for noise prediction in latent space. Additionally, we propose a predictive loss to guide training toward accurate cross-domain translation and explore several training strategies to improve stability. Our approach supports arbitrary modality pairs and performs strongly on diverse MT tasks, including multi-view to 3D shape generation, image super-resolution, and multi-view scene synthesis. Comprehensive experiments and ablations validate the effectiveness of our framework, establishing a new strong baseline in general modality translation. For more information, see our project page: https://sites.google.com/view/lddbm/home. --- ### Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge Authors: Nimrod Berman, Omkar Joglekar, Eitan Kosman, Dotan Di Castro, Omri Azencot Published: 2025-10-23 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20819v1 Recent advances in generative modeling have positioned diffusion models as state-of-the-art tools for sampling from complex data distributions. While these models have shown remarkable success across single-modality domains such as images and audio, extending their capabilities to Modality Translation (MT), translating information across different sensory modalities, remains an open challenge. Existing approaches often rely on restrictive assumptions, including shared dimensionality, Gaussian source priors, and modality-specific architectures, which limit their generality and theoretical grounding. In this work, we propose the Latent Denoising Diffusion Bridge Model (LDDBM), a general-purpose framework for modality translation based on a latent-variable extension of Denoising Diffusion Bridge Models. By operating in a shared latent space, our method learns a bridge between arbitrary modalities without requiring aligned dimensions. We introduce a contrastive alignment loss to enforce semantic consistency between paired samples and design a domain-agnostic encoder-decoder architecture tailored for noise prediction in latent space. Additionally, we propose a predictive loss to guide training toward accurate cross-domain translation and explore several training strategies to improve stability. Our approach supports arbitrary modality pairs and performs strongly on diverse MT tasks, including multi-view to 3D shape generation, image super-resolution, and multi-view scene synthesis. Comprehensive experiments and ablations validate the effectiveness of our framework, establishing a new strong baseline in general modality translation. For more information, see our project page: https://sites.google.com/view/lddbm/home. --- ### VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation Authors: Mateo Guaman Castro, Sidharth Rajagopal, Daniel Gorbatov, Matt Schmittle, Rohan Baijal, Octi Zhang, Rosario Scalise, Sidharth Talia, Emma Romig, Celso de Melo, Byron Boots, Abhishek Gupta Published: 2025-10-23 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20818v1 A fundamental challenge in robot navigation lies in learning policies that generalize across diverse environments while conforming to the unique physical constraints and capabilities of a specific embodiment (e.g., quadrupeds can walk up stairs, but rovers cannot). We propose VAMOS, a hierarchical VLA that decouples semantic planning from embodiment grounding: a generalist planner learns from diverse, open-world data, while a specialist affordance model learns the robot's physical constraints and capabilities in safe, low-cost simulation. We enabled this separation by carefully designing an interface that lets a high-level planner propose candidate paths directly in image space that the affordance model then evaluates and re-ranks. Our real-world experiments show that VAMOS achieves higher success rates in both indoor and complex outdoor navigation than state-of-the-art model-based and end-to-end learning methods. We also show that our hierarchical design enables cross-embodied navigation across legged and wheeled robots and is easily steerable using natural language. Real-world ablations confirm that the specialist model is key to embodiment grounding, enabling a single high-level planner to be deployed across physically distinct wheeled and legged robots. Finally, this model significantly enhances single-robot reliability, achieving 3X higher success rates by rejecting physically infeasible plans. Website: https://vamos-vla.github.io/ --- ### KL-Regularized Reinforcement Learning is Designed to Mode Collapse Authors: Anthony GX-Chen, Jatin Prakash, Jeff Guo, Rob Fergus, Rajesh Ranganath Published: 2025-10-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.20817v1 It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We show -- mathematically and empirically -- that this intuition does not necessarily transfer well to doing reinforcement learning with reverse/forward KL regularization (e.g. as commonly used with language models). Instead, the choice of reverse/forward KL determines the family of optimal target distributions, parameterized by the regularization coefficient. Mode coverage depends primarily on other factors, such as regularization strength, and relative scales between rewards and reference probabilities. Further, we show commonly used settings such as low regularization strength and equal verifiable rewards tend to specify unimodal target distributions, meaning the optimization objective is, by construction, non-diverse. We leverage these insights to construct a simple, scalable, and theoretically justified algorithm. It makes minimal changes to reward magnitudes, yet optimizes for a target distribution which puts high probability over all high-quality sampling modes. In experiments, this simple modification works to post-train both Large Language Models and Chemical Language Models to have higher solution quality and diversity, without any external signals of diversity, and works with both forward and reverse KL when using either naively fails. --- ### SpectraMorph: Structured Latent Learning for Self-Supervised Hyperspectral Super-Resolution Authors: Ritik Shah, Marco F Duarte Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20814v1 Hyperspectral sensors capture dense spectra per pixel but suffer from low spatial resolution, causing blurred boundaries and mixed-pixel effects. Co-registered companion sensors such as multispectral, RGB, or panchromatic cameras provide high-resolution spatial detail, motivating hyperspectral super-resolution through the fusion of hyperspectral and multispectral images (HSI-MSI). Existing deep learning based methods achieve strong performance but rely on opaque regressors that lack interpretability and often fail when the MSI has very few bands. We propose SpectraMorph, a physics-guided self-supervised fusion framework with a structured latent space. Instead of direct regression, SpectraMorph enforces an unmixing bottleneck: endmember signatures are extracted from the low-resolution HSI, and a compact multilayer perceptron predicts abundance-like maps from the MSI. Spectra are reconstructed by linear mixing, with training performed in a self-supervised manner via the MSI sensor's spectral response function. SpectraMorph produces interpretable intermediates, trains in under a minute, and remains robust even with a single-band (pan-chromatic) MSI. Experiments on synthetic and real-world datasets show SpectraMorph consistently outperforming state-of-the-art unsupervised/self-supervised baselines while remaining very competitive against supervised baselines. --- ### GSWorld: Closed-Loop Photo-Realistic Simulation Suite for Robotic Manipulation Authors: Guangqi Jiang, Haoran Chang, Ri-Zhao Qiu, Yutong Liang, Mazeyu Ji, Jiyue Zhu, Zhao Dong, Xueyan Zou, Xiaolong Wang Published: 2025-10-23 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.20813v1 This paper presents GSWorld, a robust, photo-realistic simulator for robotics manipulation that combines 3D Gaussian Splatting with physics engines. Our framework advocates "closing the loop" of developing manipulation policies with reproducible evaluation of policies learned from real-robot data and sim2real policy training without using real robots. To enable photo-realistic rendering of diverse scenes, we propose a new asset format, which we term GSDF (Gaussian Scene Description File), that infuses Gaussian-on-Mesh representation with robot URDF and other objects. With a streamlined reconstruction pipeline, we curate a database of GSDF that contains 3 robot embodiments for single-arm and bimanual manipulation, as well as more than 40 objects. Combining GSDF with physics engines, we demonstrate several immediate interesting applications: (1) learning zero-shot sim2real pixel-to-action manipulation policy with photo-realistic rendering, (2) automated high-quality DAgger data collection for adapting policies to deployment environments, (3) reproducible benchmarking of real-robot manipulation policies in simulation, (4) simulation data collection by virtual teleoperation, and (5) zero-shot sim2real visual reinforcement learning. Website: https://3dgsworld.github.io/. --- ### Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation Authors: Yuhan Liu, Lianhui Qin, Shengjie Wang Published: 2025-10-23 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.20812v4 Large Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet they struggle when reasoning over information-intensive images that densely interleave textual annotations with fine-grained graphical elements. The main challenges lie in precisely localizing critical cues in dense layouts and multi-hop reasoning to integrate dispersed evidence. We propose Speculative Verdict (SV), a training-free framework inspired by speculative decoding that combines multiple lightweight draft experts with a large verdict model. In the draft stage, small VLMs act as draft experts to generate reasoning paths that provide diverse localization candidates; in the verdict stage, a strong VLM synthesizes these paths to produce the final answer, minimizing computational cost while recovering correct answers. To further improve efficiency and accuracy, SV introduces a consensus expert selection mechanism that forwards only high-agreement reasoning paths to the verdict. Empirically, SV achieves consistent gains on challenging information-intensive and high-resolution visual question answering benchmarks, including InfographicVQA, ChartMuseum, ChartQAPro, and HR-Bench 4K. By synthesizing correct insights from multiple partially accurate reasoning paths, SV achieves both error correction and cost-efficiency compared to large proprietary models or training pipelines. Code is available at https://github.com/Tinaliu0123/speculative-verdict. --- ### Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation Authors: Yuhan Liu, Lianhui Qin, Shengjie Wang Published: 2025-10-23 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.20812v1 Large Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet they struggle when reasoning over information-intensive images that densely interleave textual annotations with fine-grained graphical elements. The main challenges lie in precisely localizing critical cues in dense layouts and multi-hop reasoning to integrate dispersed evidence. We propose Speculative Verdict (SV), a training-free framework inspired by speculative decoding that combines multiple lightweight draft experts with a large verdict model. In the draft stage, small VLMs act as draft experts to generate reasoning paths that provide diverse localization candidates; in the verdict stage, a strong VLM synthesizes these paths to produce the final answer, minimizing computational cost while recovering correct answers. To further improve efficiency and accuracy, SV introduces a consensus expert selection mechanism that forwards only high-agreement reasoning paths to the verdict. Empirically, SV achieves consistent gains on challenging information-intensive and high-resolution visual question answering benchmarks, including InfographicVQA, ChartMuseum, ChartQAPro, and HR-Bench 4K. By synthesizing correct insights from multiple partially accurate reasoning paths, SV achieves both error correction and cost-efficiency compared to large proprietary models or training pipelines. Code is available at https://github.com/Tinaliu0123/speculative-verdict --- ### On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text? Authors: Mingmeng Geng, Thierry Poibeau Published: 2025-10-23 Categories: cs.CL, cs.AI, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2510.20810v1 With the widespread use of large language models (LLMs), many researchers have turned their attention to detecting text generated by them. However, there is no consistent or precise definition of their target, namely "LLM-generated text". Differences in usage scenarios and the diversity of LLMs further increase the difficulty of detection. What is commonly regarded as the detecting target usually represents only a subset of the text that LLMs can potentially produce. Human edits to LLM outputs, together with the subtle influences that LLMs exert on their users, are blurring the line between LLM-generated and human-written text. Existing benchmarks and evaluation approaches do not adequately address the various conditions in real-world detector applications. Hence, the numerical results of detectors are often misunderstood, and their significance is diminishing. Therefore, detectors remain useful under specific conditions, but their results should be interpreted only as references rather than decisive indicators. --- ### Real Deep Research for AI, Robotics and Beyond Authors: Xueyan Zou, Jianglong Ye, Hao Zhang, Xiaoyu Xiang, Mingyu Ding, Zhaojing Yang, Yong Jae Lee, Zhuowen Tu, Sifei Liu, Xiaolong Wang Published: 2025-10-23 Categories: cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.20809v1 With the rapid growth of research in AI and robotics now producing over 10,000 papers annually it has become increasingly difficult for researchers to stay up to date. Fast evolving trends, the rise of interdisciplinary work, and the need to explore domains beyond one's expertise all contribute to this challenge. To address these issues, we propose a generalizable pipeline capable of systematically analyzing any research area: identifying emerging trends, uncovering cross domain opportunities, and offering concrete starting points for new inquiry. In this work, we present Real Deep Research (RDR) a comprehensive framework applied to the domains of AI and robotics, with a particular focus on foundation models and robotics advancements. We also briefly extend our analysis to other areas of science. The main paper details the construction of the RDR pipeline, while the appendix provides extensive results across each analyzed topic. We hope this work sheds light for researchers working in the field of AI and beyond. --- ### The Reality Gap in Robotics: Challenges, Solutions, and Best Practices Authors: Elie Aljalbout, Jiaxu Xing, Angel Romero, Iretiayo Akinola, Caelan Reed Garrett, Eric Heiden, Abhishek Gupta, Tucker Hermans, Yashraj Narang, Dieter Fox, Davide Scaramuzza, Fabio Ramos Published: 2025-10-23 Categories: cs.RO, cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.20808v1 Machine learning has facilitated significant advancements across various robotics domains, including navigation, locomotion, and manipulation. Many such achievements have been driven by the extensive use of simulation as a critical tool for training and testing robotic systems prior to their deployment in real-world environments. However, simulations consist of abstractions and approximations that inevitably introduce discrepancies between simulated and real environments, known as the reality gap. These discrepancies significantly hinder the successful transfer of systems from simulation to the real world. Closing this gap remains one of the most pressing challenges in robotics. Recent advances in sim-to-real transfer have demonstrated promising results across various platforms, including locomotion, navigation, and manipulation. By leveraging techniques such as domain randomization, real-to-sim transfer, state and action abstractions, and sim-real co-training, many works have overcome the reality gap. However, challenges persist, and a deeper understanding of the reality gap's root causes and solutions is necessary. In this survey, we present a comprehensive overview of the sim-to-real landscape, highlighting the causes, solutions, and evaluation metrics for the reality gap and sim-to-real transfer. --- ### Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers Authors: Dean L Slack, G Thomas Hudson, Thomas Winterbottom, Noura Al Moubayed Published: 2025-10-23 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.20807v1 Inspired by the performance and scalability of autoregressive large language models (LLMs), transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a simple end-to-end approach, comparing various spatiotemporal self-attention layouts. Focusing on causal modeling of physical simulations over time; a common shortcoming of existing video-generative approaches, we attempt to isolate spatiotemporal reasoning via physical object tracking metrics and unsupervised training on physical simulation datasets. We introduce a simple yet effective pure transformer model for autoregressive video prediction, utilizing continuous pixel-space representations for video prediction. Without the need for complex training strategies or latent feature-learning components, our approach significantly extends the time horizon for physically accurate predictions by up to 50% when compared with existing latent-space approaches, while maintaining comparable performance on common video quality metrics. In addition, we conduct interpretability experiments to identify network regions that encode information useful to perform accurate estimations of PDE simulation parameters via probing models, and find that this generalizes to the estimation of out-of-distribution simulation parameters. This work serves as a platform for further attention-based spatiotemporal modeling of videos via a simple, parameter efficient, and interpretable approach. --- ### ARGenSeg: Image Segmentation with Autoregressive Image Generation Model Authors: Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20803v2 We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framework. Prior works integrating image segmentation into multimodal large language models (MLLMs) typically employ either boundary points representation or dedicated segmentation heads. These methods rely on discrete representations or semantic prompts fed into task-specific decoders, which limits the ability of the MLLM to capture fine-grained visual details. To address these challenges, we introduce a segmentation framework for MLLM based on image generation, which naturally produces dense masks for target objects. We leverage MLLM to output visual tokens and detokenize them into images using an universal VQ-VAE, making the segmentation fully dependent on the pixel-level understanding of the MLLM. To reduce inference latency, we employ a next-scale-prediction strategy to generate required visual tokens in parallel. Extensive experiments demonstrate that our method surpasses prior state-of-the-art approaches on multiple segmentation datasets with a remarkable boost in inference speed, while maintaining strong understanding capabilities. --- ### ARGenSeg: Image Segmentation with Autoregressive Image Generation Model Authors: Xiaolong Wang, Lixiang Ru, Ziyuan Huang, Kaixiang Ji, Dandan Zheng, Jingdong Chen, Jun Zhou Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20803v1 We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framework. Prior works integrating image segmentation into multimodal large language models (MLLMs) typically employ either boundary points representation or dedicated segmentation heads. These methods rely on discrete representations or semantic prompts fed into task-specific decoders, which limits the ability of the MLLM to capture fine-grained visual details. To address these challenges, we introduce a segmentation framework for MLLM based on image generation, which naturally produces dense masks for target objects. We leverage MLLM to output visual tokens and detokenize them into images using an universal VQ-VAE, making the segmentation fully dependent on the pixel-level understanding of the MLLM. To reduce inference latency, we employ a next-scale-prediction strategy to generate required visual tokens in parallel. Extensive experiments demonstrate that our method surpasses prior state-of-the-art approaches on multiple segmentation datasets with a remarkable boost in inference speed, while maintaining strong understanding capabilities. --- ### Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples Authors: Shiva Sreeram, Alaa Maalouf, Pratyusha Sharma, Daniela Rus Published: 2025-10-23 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2510.20800v1 Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matrices can boost downstream accuracy -- without any gradient-based fine-tuning. Yet LASER's exhaustive, per-matrix search (each requiring full-dataset forward passes) makes it impractical for rapid deployment. We demonstrate that this overhead can be removed and find that: (i) Only a small, carefully chosen subset of matrices needs to be inspected -- eliminating the layer-by-layer sweep, (ii) The gradient of each matrix's singular values pinpoints which matrices merit reduction, (iii) Increasing the factorization search space by allowing matrices rows to cluster around multiple subspaces and then decomposing each cluster separately further reduces overfitting on the original training data and further lifts accuracy by up to 24.6 percentage points, and finally, (iv) we discover that evaluating on just 100 samples rather than the full training data -- both for computing the indicative gradients and for measuring the final accuracy -- suffices to further reduce the search time; we explain that as adaptation to downstream tasks is dominated by prompting style, not dataset size. As a result, we show that combining these findings yields a fast and robust adaptation algorithm for downstream tasks. Overall, with a single gradient step on 100 examples and a quick scan of the top candidate layers and factorization techniques, we can adapt LLMs to new datasets -- entirely without fine-tuning. --- ### No Mean Feat: Simple, Strong Baselines for Context Compression Authors: Yair Feldman, Yoav Artzi Published: 2025-10-23 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20797v2 Context compression reduces Transformer inference costs by replacing lengthy inputs with shorter pre-computed representations. It carries significant benefits for retrieval-augmented generation (RAG) and has attracted growing research attention. However, progress remains difficult to measure due to inconsistent evaluations and baselines. We design a standard, easy-to-reproduce evaluation suite for context compression, BenchPress, along with simple, high-performance baselines for English reading comprehension. BenchPress supports benchmarking across model scales, datasets, compression ratios, and short ($<$1K tokens) to mid-range ($<$8K tokens) contexts. While the suite is applicable to any compression paradigm, our baselines target soft context compression. We establish two simple baselines that strongly outperform the widely used causal compression-token approach: mean pooling and a bidirectional compression-token variant. Our results show the benefit of bidirectional attention when computing compressed representations, and that simple pooling is an expressive compression operator. --- ### Simple Context Compression: Mean-Pooling and Multi-Ratio Training Authors: Yair Feldman, Yoav Artzi Published: 2025-10-23 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20797v1 A common strategy to reduce the computational costs of using long contexts in retrieval-augmented generation (RAG) with large language models (LLMs) is soft context compression, where the input sequence is transformed into a shorter continuous representation. We develop a lightweight and simple mean-pooling approach that consistently outperforms the widely used compression-tokens architecture, and study training the same compressor to output multiple compression ratios. We conduct extensive experiments across in-domain and out-of-domain QA datasets, as well as across model families, scales, and compression ratios. Overall, our simple mean-pooling approach achieves the strongest performance, with a relatively small drop when training for multiple compression ratios. More broadly though, across architectures and training regimes the trade-offs are more nuanced, illustrating the complex landscape of compression methods. --- ### Bayesian Inference of Primordial Magnetic Field Parameters from CMB with Spherical Graph Neural Networks Authors: Juan Alejandro Pinto Castro, Héctor J. Hortúa, Jorge Enrique García-Farieta, Roger Anderson Hurtado Published: 2025-10-23 Categories: astro-ph.CO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20795v1 Deep learning has emerged as a transformative methodology in modern cosmology, providing powerful tools to extract meaningful physical information from complex astronomical datasets. This paper implements a novel Bayesian graph deep learning framework for estimating key cosmological parameters in a primordial magnetic field (PMF) cosmology directly from simulated Cosmic Microwave Background (CMB) maps. Our methodology utilizes DeepSphere, a spherical convolutional neural network architecture specifically designed to respect the spherical geometry of CMB data through HEALPix pixelization. To advance beyond deterministic point estimates and enable robust uncertainty quantification, we integrate Bayesian Neural Networks (BNNs) into the framework, capturing aleatoric and epistemic uncertainties that reflect the model confidence in its predictions. The proposed approach demonstrates exceptional performance, achieving $R^{2}$ scores exceeding 0.89 for the magnetic parameter estimation. We further obtain well-calibrated uncertainty estimates through post-hoc training techniques including Variance Scaling and GPNormal. This integrated DeepSphere-BNNs framework not only delivers accurate parameter estimation from CMB maps with PMF contributions but also provides reliable uncertainty quantification, providing the necessary tools for robust cosmological inference in the era of precision cosmology. --- ### Radar-Camera Fused Multi-Object Tracking: Online Calibration and Common Feature Authors: Lei Cheng, Siyang Cao Published: 2025-10-23 Categories: cs.CV, eess.SP arXiv: https://arxiv.org/abs/2510.20794v1 This paper presents a Multi-Object Tracking (MOT) framework that fuses radar and camera data to enhance tracking efficiency while minimizing manual interventions. Contrary to many studies that underutilize radar and assign it a supplementary role--despite its capability to provide accurate range/depth information of targets in a world 3D coordinate system--our approach positions radar in a crucial role. Meanwhile, this paper utilizes common features to enable online calibration to autonomously associate detections from radar and camera. The main contributions of this work include: (1) the development of a radar-camera fusion MOT framework that exploits online radar-camera calibration to simplify the integration of detection results from these two sensors, (2) the utilization of common features between radar and camera data to accurately derive real-world positions of detected objects, and (3) the adoption of feature matching and category-consistency checking to surpass the limitations of mere position matching in enhancing sensor association accuracy. To the best of our knowledge, we are the first to investigate the integration of radar-camera common features and their use in online calibration for achieving MOT. The efficacy of our framework is demonstrated by its ability to streamline the radar-camera mapping process and improve tracking precision, as evidenced by real-world experiments conducted in both controlled environments and actual traffic scenarios. Code is available at https://github.com/radar-lab/Radar_Camera_MOT --- ### BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation Authors: Liang Ye, Shengqin Chen, Jiazhu Dai Published: 2025-10-23 Categories: cs.LG, cs.CL, q-bio.BM arXiv: https://arxiv.org/abs/2510.20792v5 The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. Though prior work has explored backdoor attacks against diffusion models for image or unconditional graph generation, those against conditional graph generation models, especially text-guided graph generation models, remain largely unexamined. This paper proposes BadGraph, a backdoor attack method against latent diffusion models for text-guided graph generation. BadGraph leverages textual triggers to poison training data, covertly implanting backdoors that induce attacker-specified subgraphs during inference when triggers appear, while preserving normal performance on clean inputs. Extensive experiments on four benchmark datasets (PubChem, ChEBI-20, PCDes, MoMu) demonstrate the effectiveness and stealth of the attack: a poisoning rate of less than 10% can achieve a 50% attack success rate, while 24% suffices for over an 80% success rate, with negligible performance degradation on benign samples. Ablation studies further reveal that the backdoor is implanted during VAE and diffusion training rather than pretraining. These findings reveal the security vulnerabilities in latent diffusion models for text-guided graph generation, highlight the serious risks in applications such as drug discovery, and underscore the need for robust defenses against the backdoor attack in such diffusion models. --- ### BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation Authors: Liang Ye, Shengqin Chen, Jiazhu Dai Published: 2025-10-23 Categories: cs.LG, cs.CL, q-bio.BM arXiv: https://arxiv.org/abs/2510.20792v1 The rapid progress of graph generation has raised new security concerns, particularly regarding backdoor vulnerabilities. While prior work has explored backdoor attacks in image diffusion and unconditional graph generation, conditional, especially text-guided graph generation remains largely unexamined. This paper proposes BadGraph, a backdoor attack method targeting latent diffusion models for text-guided graph generation. BadGraph leverages textual triggers to poison training data, covertly implanting backdoors that induce attacker-specified subgraphs during inference when triggers appear, while preserving normal performance on clean inputs. Extensive experiments on four benchmark datasets (PubChem, ChEBI-20, PCDes, MoMu) demonstrate the effectiveness and stealth of the attack: less than 10% poisoning rate can achieves 50% attack success rate, while 24% suffices for over 80% success rate, with negligible performance degradation on benign samples. Ablation studies further reveal that the backdoor is implanted during VAE and diffusion training rather than pretraining. These findings reveal the security vulnerabilities in latent diffusion models of text-guided graph generation, highlight the serious risks in models' applications such as drug discovery and underscore the need for robust defenses against the backdoor attack in such diffusion models. --- ### Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction Authors: Mutian He, Philip N. Garner Published: 2025-10-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.20787v2 Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To mitigate the issue, we explore a series of hybrid models that restore direct access to past tokens. We interleave token mixers with intermediate time and space complexity between linear and full attention, including sparse attention with token eviction, and the query-aware native sparse attention. Particularly, we propose a novel learnable token eviction approach. Combined with sliding-window attention, an end-to-end trainable lightweight CNN aggregates information from both past and future adjacent tokens to adaptively retain a limited set of critical KV-pairs per head, maintaining linear attention's constant time and space complexity. Efficient Triton kernels for the sparse attention mechanisms are provided. Empirical evaluations on retrieval-intensive benchmarks support the effectiveness of our approaches. --- ### Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction Authors: Mutian He, Philip N. Garner Published: 2025-10-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.20787v1 Linear-attention models that compress the entire input sequence into a fixed-size recurrent state offer an efficient alternative to Transformers, but their finite memory induces forgetfulness that harms retrieval-intensive tasks. To mitigate the issue, we explore a series of hybrid models that restore direct access to past tokens. We interleave token mixers with intermediate time and space complexity between linear and full attention, including sparse attention with token eviction, and the query-aware native sparse attention. Particularly, we propose a novel learnable token eviction approach. Combined with sliding-window attention, an end-to-end trainable lightweight CNN aggregates information from both past and future adjacent tokens to adaptively retain a limited set of critical KV-pairs per head, maintaining linear attention's constant time and space complexity. Efficient Triton kernels for the sparse attention mechanisms are provided. Empirical evaluations on retrieval-intensive benchmarks support the effectiveness of our approaches. --- ### A Coherence-Based Measure of AGI Authors: Fares Fourati Published: 2025-10-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20784v2 Recent approaches to evaluating Artificial General Intelligence (AGI) typically summarize a system's capability using the arithmetic mean of its proficiencies across multiple cognitive domains. While simple, this implicitly assumes compensability: exceptional performance in some areas can offset severe deficiencies in others. Genuine general intelligence, however, requires coherent sufficiency: balanced competence across all essential faculties. We introduce a coherence-based measure of AGI that integrates the generalized mean over a continuum of compensability exponents. This yields an area-under-the-curve (AUC) metric spanning arithmetic, geometric, and harmonic regimes, quantifying how robust an evaluated capability remains as compensability assumptions become stricter. Unlike the arithmetic mean, which rewards specialization, the AUC penalizes imbalance and exposes bottlenecks that constrain performance. To illustrate the framework, we apply it to cognitive profiles derived from the Cattell-Horn-Carroll (CHC) model, showing how coherence-based aggregation highlights imbalances that are obscured by arithmetic averaging. As a second, independent example, we apply the same methodology to a set of 17 heterogeneous benchmarks, demonstrating how coherence-based evaluation can reveal unevenness even in narrower task collections. These examples show that the proposed approach offers a principled, interpretable, and stricter foundation for measuring progress toward AGI. --- ### A Coherence-Based Measure of AGI Authors: Fares Fourati Published: 2025-10-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.20784v1 Recent work by \citet{hendrycks2025agidefinition} formalized \textit{Artificial General Intelligence} (AGI) as the arithmetic mean of proficiencies across cognitive domains derived from the Cattell--Horn--Carroll (CHC) model of human cognition. While elegant, this definition assumes \textit{compensability} -- that exceptional ability in some domains can offset failure in others. True general intelligence, however, should reflect \textit{coherent sufficiency}: balanced competence across all essential domains. We propose a coherence-aware measure of AGI based on the integral of generalized means over a continuum of compensability exponents. This formulation spans arithmetic, geometric, and harmonic regimes, and the resulting \textit{area under the curve} (AUC) quantifies robustness under varying compensability assumptions. Unlike the arithmetic mean, which rewards specialization, the AUC penalizes imbalance and captures inter-domain dependency. Applied to published CHC-based domain scores for GPT-4 and GPT-5, the coherence-adjusted AUC reveals that both systems remain far from general competence despite high arithmetic scores (e.g., GPT-5 at~24\%). Integrating the generalized mean thus yields a principled, interpretable, and stricter foundation for measuring genuine progress toward AGI. --- ### Out-of-distribution Tests Reveal Compositionality in Chess Transformers Authors: Anna Mészáros, Patrik Reizinger, Ferenc Huszár Published: 2025-10-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.20783v1 Chess is a canonical example of a task that requires rigorous reasoning and long-term planning. Modern decision Transformers - trained similarly to LLMs - are able to learn competent gameplay, but it is unclear to what extent they truly capture the rules of chess. To investigate this, we train a 270M parameter chess Transformer and test it on out-of-distribution scenarios, designed to reveal failures of systematic generalization. Our analysis shows that Transformers exhibit compositional generalization, as evidenced by strong rule extrapolation: they adhere to fundamental syntactic rules of the game by consistently choosing valid moves even in situations very different from the training data. Moreover, they also generate high-quality moves for OOD puzzles. In a more challenging test, we evaluate the models on variants including Chess960 (Fischer Random Chess) - a variant of chess where starting positions of pieces are randomized. We found that while the model exhibits basic strategy adaptation, they are inferior to symbolic AI algorithms that perform explicit search, but gap is smaller when playing against users on Lichess. Moreover, the training dynamics revealed that the model initially learns to move only its own pieces, suggesting an emergent compositional understanding of the game. --- ### A Use-Case Specific Dataset for Measuring Dimensions of Responsible Performance in LLM-generated Text Authors: Alicia Sagae, Chia-Jung Lee, Sandeep Avula, Brandon Dang, Vanessa Murdock Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.20782v1 Current methods for evaluating large language models (LLMs) typically focus on high-level tasks such as text generation, without targeting a particular AI application. This approach is not sufficient for evaluating LLMs for Responsible AI dimensions like fairness, since protected attributes that are highly relevant in one application may be less relevant in another. In this work, we construct a dataset that is driven by a real-world application (generate a plain-text product description, given a list of product features), parameterized by fairness attributes intersected with gendered adjectives and product categories, yielding a rich set of labeled prompts. We show how to use the data to identify quality, veracity, safety, and fairness gaps in LLMs, contributing a proposal for LLM evaluation paired with a concrete resource for the research community. --- ### Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost Authors: Runzhe Zhan, Zhihong Huang, Xinyi Yang, Lidia S. Chao, Min Yang, Derek F. Wong Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.20780v1 Recent advancements in large reasoning models (LRMs) have introduced an intermediate "thinking" process prior to generating final answers, improving their reasoning capabilities on complex downstream tasks. However, the potential of LRMs as evaluators for machine translation (MT) quality remains underexplored. We provides the first systematic analysis of LRM-as-a-judge in MT evaluation. We identify key challenges, revealing LRMs require tailored evaluation materials, tend to "overthink" simpler instances and have issues with scoring mechanisms leading to overestimation. To address these, we propose to calibrate LRM thinking by training them on synthetic, human-like thinking trajectories. Our experiments on WMT24 Metrics benchmarks demonstrate that this approach largely reduces thinking budgets by ~35x while concurrently improving evaluation performance across different LRM scales from 7B to 32B (e.g., R1-Distill-Qwen-7B achieves a +8.7 correlation point improvement). These findings highlight the potential of efficiently calibrated LRMs to advance fine-grained automatic MT evaluation. --- ### CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling Authors: Binbin Huang, Haobin Duan, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20776v2 We introduce Cupid, a generative 3D reconstruction framework that jointly models the full distribution over both canonical objects and camera poses. Our two-stage flow-based model first generates a coarse 3D structure and 2D-3D correspondences to estimate the camera pose robustly. Conditioned on this pose, a refinement stage injects pixel-aligned image features directly into the generative process, marrying the rich prior of a generative model with the geometric fidelity of reconstruction. This strategy achieves exceptional faithfulness, outperforming state-of-the-art reconstruction methods by over 3 dB PSNR and 10% in Chamfer Distance. As a unified generative model that decouples the object and camera pose, Cupid naturally extends to multi-view and scene-level reconstruction tasks without requiring post-hoc optimization or fine-tuning. --- ### CUPID: Pose-Grounded Generative 3D Reconstruction from a Single Image Authors: Binbin Huang, Haobin Duan, Yiqun Zhao, Zibo Zhao, Yi Ma, Shenghua Gao Published: 2025-10-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.20776v1 This work proposes a new generation-based 3D reconstruction method, named Cupid, that accurately infers the camera pose, 3D shape, and texture of an object from a single 2D image. Cupid casts 3D reconstruction as a conditional sampling process from a learned distribution of 3D objects, and it jointly generates voxels and pixel-voxel correspondences, enabling robust pose and shape estimation under a unified generative framework. By representing both input camera poses and 3D shape as a distribution in a shared 3D latent space, Cupid adopts a two-stage flow matching pipeline: (1) a coarse stage that produces initial 3D geometry with associated 2D projections for pose recovery; and (2) a refinement stage that integrates pose-aligned image features to enhance structural fidelity and appearance details. Extensive experiments demonstrate Cupid outperforms leading 3D reconstruction methods with an over 3 dB PSNR gain and an over 10% Chamfer Distance reduction, while matching monocular estimators on pose accuracy and delivering superior visual fidelity over baseline 3D generative models. For an immersive view of the 3D results generated by Cupid, please visit cupid3d.github.io. --- ### FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation Authors: Wenhao Wang, Kehe Ye, Xinyu Zhou, Tianxing Chen, Cao Min, Qiaoming Zhu, Xiaokang Yang, Ping Luo, Yongjian Shen, Yang Yang, Maoqing Yao, Yao Mu Published: 2025-10-23 Categories: cs.RO, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2510.20774v2 Large-scale and diverse datasets are vital for training robust robotic manipulation policies, yet existing data collection methods struggle to balance scale, diversity, and quality. Simulation offers scalability but suffers from sim-to-real gaps, while teleoperation yields high-quality demonstrations with limited diversity and high labor cost. We introduce FieldGen, a field-guided data generation framework that enables scalable, diverse, and high-quality real-world data collection with minimal human supervision. FieldGen decomposes manipulation into two stages: a pre-manipulation phase, allowing trajectory diversity, and a fine manipulation phase requiring expert precision. Human demonstrations capture key contact and pose information, after which an attraction field automatically generates diverse trajectories converging to successful configurations. This decoupled design combines scalable trajectory diversity with precise supervision. Moreover, FieldGen-Reward augments generated data with reward annotations to further enhance policy learning. Experiments demonstrate that policies trained with FieldGen achieve higher success rates and improved stability compared to teleoperation-based baselines, while significantly reducing human effort in long-term real-world data collection. Webpage is available at https://fieldgen.github.io/. --- ### FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generation Authors: Wenhao Wang, Kehe Ye, Xinyu Zhou, Tianxing Chen, Cao Min, Qiaoming Zhu, Xiaokang Yang, Yongjian Shen, Yang Yang, Maoqing Yao, Yao Mu Published: 2025-10-23 Categories: cs.RO, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2510.20774v1 Large-scale and diverse datasets are vital for training robust robotic manipulation policies, yet existing data collection methods struggle to balance scale, diversity, and quality. Simulation offers scalability but suffers from sim-to-real gaps, while teleoperation yields high-quality demonstrations with limited diversity and high labor cost. We introduce FieldGen, a field-guided data generation framework that enables scalable, diverse, and high-quality real-world data collection with minimal human supervision. FieldGen decomposes manipulation into two stages: a pre-manipulation phase, allowing trajectory diversity, and a fine manipulation phase requiring expert precision. Human demonstrations capture key contact and pose information, after which an attraction field automatically generates diverse trajectories converging to successful configurations. This decoupled design combines scalable trajectory diversity with precise supervision. Moreover, FieldGen-Reward augments generated data with reward annotations to further enhance policy learning. Experiments demonstrate that policies trained with FieldGen achieve higher success rates and improved stability compared to teleoperation-based baselines, while significantly reducing human effort in long-term real-world data collection. Webpage is available at https://fieldgen.github.io/. --- ### AlphaFlow: Understanding and Improving MeanFlow Models Authors: Huijie Zhang, Aliaksandr Siarohin, Willi Menapace, Michael Vasilkovsky, Sergey Tulyakov, Qing Qu, Ivan Skorokhodov Published: 2025-10-23 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.20771v1 MeanFlow has recently emerged as a powerful framework for few-step generative modeling trained from scratch, but its success is not yet fully understood. In this work, we show that the MeanFlow objective naturally decomposes into two parts: trajectory flow matching and trajectory consistency. Through gradient analysis, we find that these terms are strongly negatively correlated, causing optimization conflict and slow convergence. Motivated by these insights, we introduce $α$-Flow, a broad family of objectives that unifies trajectory flow matching, Shortcut Model, and MeanFlow under one formulation. By adopting a curriculum strategy that smoothly anneals from trajectory flow matching to MeanFlow, $α$-Flow disentangles the conflicting objectives, and achieves better convergence. When trained from scratch on class-conditional ImageNet-1K 256x256 with vanilla DiT backbones, $α$-Flow consistently outperforms MeanFlow across scales and settings. Our largest $α$-Flow-XL/2+ model achieves new state-of-the-art results using vanilla DiT backbones, with FID scores of 2.58 (1-NFE) and 2.15 (2-NFE). --- ### CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting Authors: Tianyi Xiong, Haonan Chen, Kelly Mahoney, Jingyin Tang, Tim Smith, Janice Bytheway Published: 2025-10-23 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2510.20769v2 Accurate medium-range precipitation forecasting is essential for hydrometeorological risk management but remains challenging for both numerical weather prediction (NWP) systems and data-driven models. We present CSU-PCAST, a deep learning-based ensemble forecasting framework for global precipitation prediction. The model is trained using ERA5 atmospheric and surface variables at 0.25° resolution with precipitation labels from NASA's IMERG dataset. CSU-PCAST uses 57 prognostic variables and static geographical fields to predict both atmospheric states and 6-h accumulated precipitation. The framework employs a Swin Transformer backbone with stochastic noise conditioning, temporal embeddings, and a dual-branch decoder for precipitation and non-precipitation variables. During inference, CSU-PCAST is initialized from operational GFS analyses and generates 30 ensemble members out to 15 days using an autoregressive strategy. Evaluation against GEFS over the full year of 2023 shows improved precipitation forecast skill at short lead times, including higher Critical Success Index (CSI) and lower RMSE during the first several forecast days. CSU-PCAST also reduces GEFS wet bias for light precipitation and dry bias at heavier precipitation thresholds. Probabilistic verification demonstrates lower CRPS, higher Brier Skill Scores at several thresholds, and improved ensemble reliability relative to GEFS, although both systems remain underdispersive. A case study of the Sanba extreme precipitation event further shows improved spatial structure and exceedance-probability guidance. These results demonstrate the potential of CSU-PCAST for short-to-medium-range ensemble precipitation forecasting while highlighting remaining challenges in extreme precipitation prediction and ensemble calibration. --- ### CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting Authors: Tianyi Xiong, Haonan Chen Published: 2025-10-23 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2510.20769v1 Accurate medium-range precipitation forecasting is crucial for hydrometeorological risk management and disaster mitigation, yet remains challenging for current numerical weather prediction (NWP) systems. Traditional ensemble systems such as the Global Ensemble Forecast System (GEFS) struggle to maintain high skill, especially for moderate and heavy rainfall at extended lead times. This study develops a deep learning-based ensemble framework for multi-step precipitation prediction through joint modeling of a comprehensive set of atmospheric variables. The model is trained on ERA5 reanalysis data at 0.25$^{\circ}$ spatial resolution, with precipitation labels from NASA's Integrated Multi-satellite Retrievals for Global Precipitation Measurement (GPM) constellation (IMERG), incorporating 57 input variables, including upper-air and surface predictors. The architecture employs a patch-based Swin Transformer backbone with periodic convolutions to handle longitudinal continuity and integrates time and noise embeddings through conditional layer normalization. A dual-branch decoder predicts total precipitation and other variables, with targeted freezing of encoder-decoder pathways for specialized training. Training minimizes a hybrid loss combining the Continuous Ranked Probability Score (CRPS) and weighted log1p mean squared error (log1pMSE), balancing probabilistic accuracy and magnitude fidelity. During inference, the model ingests real-time Global Forecast System (GFS) initial conditions to generate 15-day forecasts autoregressively. Evaluation against GEFS using IMERG data demonstrates higher Critical Success Index (CSI) scores at precipitation thresholds of 0.1 mm, 1 mm, 10 mm, and 20 mm, highlighting improved performance for moderate to heavy rainfall. ---