# Research Papers — 2025-10 · bundle page 77 of 217

> Full-text markdown of papers #3801–3850 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/77
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/76.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/78.md)

### Token-Level Inference-Time Alignment for Vision-Language Models

Authors: Kejia Chen, Jiawen Zhang, Jiacong Hu, Kewei Gao, Jian Lou, Zunlei Feng, Mingli Song
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.21794v1

Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on expensive fine-tuning with annotated preference data or sequence-level inference strategies that provide only coarse, delayed feedback. To overcome these limitations, we present TITA (Token-level Inference-Time Alignment), a lightweight framework that freezes the base VLM and instead trains a reward model to approximate its distribution. During inference, implicit preference signals are extracted as log-probability ratios between the reward model and the target VLM, yielding dense autoregressive feedback. This formulation can be viewed as an inference-time variant of Direct Preference Optimization (DPO), providing token-level corrective signals without retraining the backbone. Extensive evaluations on LLaVA-1.5-7B and 13B show consistent gains across 12 benchmarks, with improvements of 8.6% on MMVet and 6.7% on POPE, indicating stronger general understanding and reduced hallucinations. Additional experiments on Qwen2.5-VL-7B and DeepSeek-VL2-27.5B show comparable gains, especially in hallucination reduction and VQA accuracy, while incurring negligible inference overhead.

---

### 2D_3D Feature Fusion via Cross-Modal Latent Synthesis and Attention Guided Restoration for Industrial Anomaly Detection

Authors: Usman Ali, Ali Zia, Abdul Rehman, Umer Ramzan, Zohaib Hassan, Talha Sattar, Jing Wang, Wei Xiang
Published: 2025-10-20
Categories: cs.CV, cs.AI, eess.IV
arXiv: https://arxiv.org/abs/2510.21793v1

Industrial anomaly detection (IAD) increasingly benefits from integrating 2D and 3D data, but robust cross-modal fusion remains challenging. We propose a novel unsupervised framework, Multi-Modal Attention-Driven Fusion Restoration (MAFR), which synthesises a unified latent space from RGB images and point clouds using a shared fusion encoder, followed by attention-guided, modality-specific decoders. Anomalies are localised by measuring reconstruction errors between input features and their restored counterparts. Evaluations on the MVTec 3D-AD and Eyecandies benchmarks demonstrate that MAFR achieves state-of-the-art results, with a mean I-AUROC of 0.972 and 0.901, respectively. The framework also exhibits strong performance in few-shot learning settings, and ablation studies confirm the critical roles of the fusion architecture and composite loss. MAFR offers a principled approach for fusing visual and geometric information, advancing the robustness and accuracy of industrial anomaly detection. Code is available at https://github.com/adabrh/MAFR

---

### Variance-Reduction Guidance: Sampling Trajectory Optimization for Diffusion Models

Authors: Shifeng Xu, Yanzhu Liu, Adams Wai-Kin Kong
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.21792v1

Diffusion models have become emerging generative models. Their sampling process involves multiple steps, and in each step the models predict the noise from a noisy sample. When the models make prediction, the output deviates from the ground truth, and we call such a deviation as \textit{prediction error}. The prediction error accumulates over the sampling process and deteriorates generation quality. This paper introduces a novel technique for statistically measuring the prediction error and proposes the Variance-Reduction Guidance (VRG) method to mitigate this error. VRG does not require model fine-tuning or modification. Given a predefined sampling trajectory, it searches for a new trajectory which has the same number of sampling steps but produces higher quality results. VRG is applicable to both conditional and unconditional generation. Experiments on various datasets and baselines demonstrate that VRG can significantly improve the generation quality of diffusion models. Source code is available at https://github.com/shifengxu/VRG.

---

### Exploring the design space of diffusion and flow models for data fusion

Authors: Niraj Chaudhari, Manmeet Singh, Naveen Sudharsan, Amit Kumar Srivastava, Harsh Kamath, Dushyant Mahajan, Ayan Paul
Published: 2025-10-20
Categories: cs.CV, physics.ins-det
arXiv: https://arxiv.org/abs/2510.21791v1

Data fusion is an essential task in various domains, enabling the integration of multi-source information to enhance data quality and insights. One key application is in satellite remote sensing, where fusing multi-sensor observations can improve spatial and temporal resolution. In this study, we explore the design space of diffusion and flow models for data fusion, focusing on the integration of Defense Meteorological Satellite Program's Operational Linescan System (DMSP-OLS) and Visible Infrared Imaging Radiometer Suite (VIIRS) nighttime lights data. Our approach leverages a diverse set of 2D image-to-image generative models, including UNET, diffusion, and flow modeling architectures. We evaluate the effectiveness of these architectures in satellite remote sensing data fusion, identifying diffusion models based on UNet as particularly adept at preserving fine-grained spatial details and generating high-fidelity fused images. We also provide guidance on the selection of noise schedulers in diffusion-based models, highlighting the trade-offs between iterative solvers for faster inference and discrete schedulers for higher-quality reconstructions. Additionally, we explore quantization techniques to optimize memory efficiency and computational cost without compromising performance. Our findings offer practical insights into selecting the most effective diffusion and flow model architectures for data fusion tasks, particularly in remote sensing applications, and provide recommendations for leveraging noise scheduling strategies to enhance fusion quality.

---

### CourtGuard: A Local, Multiagent Prompt Injection Classifier

Authors: Isaac Wu, Michael Maslowski
Published: 2025-10-20
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.19844v1

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to leak sensitive data, spread misinformation, and exhibit harmful behaviors. To defend against these attacks, we propose CourtGuard, a locally-runnable, multiagent prompt injection classifier. In it, prompts are evaluated in a court-like multiagent LLM system, where a "defense attorney" model argues the prompt is benign, a "prosecution attorney" model argues the prompt is a prompt injection, and a "judge" model gives the final classification. CourtGuard has a lower false positive rate than the Direct Detector, an LLM as-a-judge. However, CourtGuard is generally a worse prompt injection detector. Nevertheless, this lower false positive rate highlights the importance of considering both adversarial and benign scenarios for the classification of a prompt. Additionally, the relative performance of CourtGuard in comparison to other prompt injection classifiers advances the use of multiagent systems as a defense against prompt injection attacks. The implementations of CourtGuard and the Direct Detector with full prompts for Gemma-3-12b-it, Llama-3.3-8B, and Phi-4-mini-instruct are available at https://github.com/isaacwu2000/CourtGuard.

---

### Evaluating LLMs for Career Guidance: Comparative Analysis of Computing Competency Recommendations Across Ten African Countries

Authors: Precious Eze, Stephanie Lunn, Bruk Berhane
Published: 2025-10-20
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.18902v2

Employers increasingly expect graduates to utilize large language models (LLMs) in the workplace, yet the competencies needed for computing roles across Africa remain unclear given varying national contexts. This study examined how six LLMs, namely ChatGPT 4, DeepSeek, Gemini, Claude 3.5, Llama 3, and Mistral AI, describe entry-level computing career expectations across ten African countries. Using the Computing Curricula 2020 framework and drawing on Digital Colonialism Theory and Ubuntu Philosophy, content analysis of 60 LLM responses to standardized prompts reveals consistent coverage of technical competencies such as cloud computing and programming, but notable differences in non-technical competencies, particularly ethics and responsible AI use. Models vary considerably in recognizing country-specific factors, including local technology ecosystems, language requirements, and national policies averaging only 35.4% contextual awareness overall. Open-source models demonstrated stronger contextual awareness and better balance between technical and professional skills, with Llama (4.47/5) and DeepSeek (4.25/5) outperforming proprietary alternatives ChatGPT-4 (3.90/5) and Claude (3.46/5). However, Mistral's poor contextual performance (0.00/4) despite being open-source indicates that development philosophy alone does not guarantee contextual responsiveness. This first comprehensive comparison of LLM career guidance for African computing students uncovers entrenched infrastructure assumptions and Western-centric biases that create gaps between technical recommendations and local realities. The findings challenge assumptions about AI tool quality in resource-constrained settings and underscore the need for decolonial approaches to AI in education, emphasizing contextual relevance and hybrid human-AI guidance models.

---

### Foundation Models for Discovery and Exploration in Chemical Space

Authors: Alexius Wadell, Anoushka Bhutani, Victor Azumah, Austin R. Ellis-Mohr, Andrew J. Stier, Kareem Hegazy, Alexander Brace, Hancheng Zhao, Celia Kelly, Anuj K. Nayak, Yuhan Chen, Dimitrios Simatos et al.
Published: 2025-10-20
Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG
arXiv: https://arxiv.org/abs/2510.18900v2

Accurate prediction of atomistic, thermodynamic, and kinetic properties from molecular structures underpins materials innovation. Existing computational and experimental approaches lack the scalability required to navigate chemical space efficiently. Scientific foundation models trained on large unlabelled datasets offer a path towards navigating chemical space across application domains. Here, we develop MIST, a family of molecular foundation models with up to an order of magnitude more parameters and data than prior works. Trained using a novel tokenizer, Smirk, which comprehensively captures nuclear, electronic, and geometric information, MIST learns a diverse range of molecules. MIST models have been fine-tuned to predict more than 400 structure-property relationships and have been shown to match or exceed state-of-the-art performance across diverse benchmarks, from physiology to electrochemistry. We demonstrate the ability of these models to solve real-world problems across chemical space from multiobjective electrolyte solvent screening to stereochemical reasoning for organometallics and mixture property prediction. The clearest demonstration of a foundation model is its ability to solve problems that were neither explicit targets of training nor central to the intentions of its developers. We identify olfactory perception mapping as such a problem, and show that MIST accurately predicted scent profiles and learned a hierarchical representation of olfactory space consistent with hyperbolic geometry. We formulated hyperparameter aware Bayesian neural scaling laws which eliminate the need for hyperparameter sweeps at every scale, making training large compute-optimal models feasible on a limited compute budget. The methods and findings presented here represent a significant step towards accelerating materials discovery, design, and optimization using foundation models.

---

### Transformer-Based Low-Resource Language Translation: A Study on Standard Bengali to Sylheti

Authors: Mangsura Kabir Oni, Tabia Tanzin Prama
Published: 2025-10-20
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.18898v1

Machine Translation (MT) has advanced from rule-based and statistical methods to neural approaches based on the Transformer architecture. While these methods have achieved impressive results for high-resource languages, low-resource varieties such as Sylheti remain underexplored. In this work, we investigate Bengali-to-Sylheti translation by fine-tuning multilingual Transformer models and comparing them with zero-shot large language models (LLMs). Experimental results demonstrate that fine-tuned models significantly outperform LLMs, with mBART-50 achieving the highest translation adequacy and MarianMT showing the strongest character-level fidelity. These findings highlight the importance of task-specific adaptation for underrepresented languages and contribute to ongoing efforts toward inclusive language technologies.

---

### AI for Distributed Systems Design: Scalable Cloud Optimization Through Repeated LLMs Sampling And Simulators

Authors: Jacopo Tagliabue
Published: 2025-10-20
Categories: cs.DC, cs.AI, cs.DB, cs.SE
arXiv: https://arxiv.org/abs/2510.18897v1

We explore AI-driven distributed-systems policy design by combining stochastic code generation from large language models (LLMs) with deterministic verification in a domain-specific simulator. Using a Function-as-a-Service runtime (Bauplan) and its open-source simulator (Eudoxia) as a case study, we frame scheduler design as an iterative generate-and-verify loop: an LLM proposes a Python policy, the simulator evaluates it on standardized traces, and structured feedback steers subsequent generations. This setup preserves interpretability while enabling targeted search over a large design space. We detail the system architecture and report preliminary results on throughput improvements across multiple models. Beyond early gains, we discuss the limits of the current setup and outline next steps; in particular, we conjecture that AI will be crucial for scaling this methodology by helping to bootstrap new simulators.

---

### CosmoCore Affective Dream-Replay Reinforcement Learning for Code Generation

Authors: Santhosh Kumar Ravindran
Published: 2025-10-20
Categories: cs.SE, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2510.18895v1

We introduce CosmoCore, a neuroscience-inspired reinforcement learning (RL) architecture that integrates affective signals to enhance code generation in large language models (LLMs). Motivated by human and animal learning where embarrassment from mistakes drives rapid correction, as observed in training a puppy to avoid repeating errors after a single scolding CosmoCore tags code generation trajectories with valence and surprise using a lightweight multi-layer perceptron (MLP). High-negative valence (cringe) episodes, such as buggy code outputs, are prioritized in a Dream Queue for five-fold replay during off-policy updates, while low-surprise successes are pruned to prevent overconfidence and buffer bloat. Evaluated on code generation benchmarks like HumanEval and BigCodeBench, alongside simulations with a custom data pipeline environment, CosmoCore reduces hallucinated code (e.g., syntax errors or logical bugs) by 48\% and accelerates self-correction by 45\%. Local experiments using Hugging Face models in a PySpark environment validate these gains, with code snippets provided for replication. Ablations confirm valence tagging boosts curiosity in exploration, and pruning mitigates inefficiency. This framework extends RL from human feedback (RLHF) for more emotionally aware code assistants, with applications in IDEs and data pipelines. Code and the custom mini-world simulation are released.

---

### OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales

Authors: Tung Nguyen, Tuan Pham, Troy Arcomano, Veerabhadra Kotamarthi, Ian Foster, Sandeep Madireddy, Aditya Grover
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.18707v1

Accurate weather forecasting across time scales is critical for anticipating and mitigating the impacts of climate change. Recent data-driven methods based on deep learning have achieved significant success in the medium range, but struggle at longer subseasonal-to-seasonal (S2S) horizons due to error accumulation in their autoregressive approach. In this work, we propose OmniCast, a scalable and skillful probabilistic model that unifies weather forecasting across timescales. OmniCast consists of two components: a VAE model that encodes raw weather data into a continuous, lower-dimensional latent space, and a diffusion-based transformer model that generates a sequence of future latent tokens given the initial conditioning tokens. During training, we mask random future tokens and train the transformer to estimate their distribution given conditioning and visible tokens using a per-token diffusion head. During inference, the transformer generates the full sequence of future tokens by iteratively unmasking random subsets of tokens. This joint sampling across space and time mitigates compounding errors from autoregressive approaches. The low-dimensional latent space enables modeling long sequences of future latent states, allowing the transformer to learn weather dynamics beyond initial conditions. OmniCast performs competitively with leading probabilistic methods at the medium-range timescale while being 10x to 20x faster, and achieves state-of-the-art performance at the subseasonal-to-seasonal scale across accuracy, physics-based, and probabilistic metrics. Furthermore, we demonstrate that OmniCast can generate stable rollouts up to 100 years ahead. Code and model checkpoints are available at https://github.com/tung-nd/omnicast.

---

### Local Coherence or Global Validity? Investigating RLVR Traces in Math Domains

Authors: Soumya Rani Samineni, Durgesh Kalwar, Vardaan Gangal, Siddhant Bhambri, Subbarao Kambhampati
Published: 2025-10-20
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.18176v1

Reinforcement Learning with Verifiable Rewards (RLVR)-based post-training of Large Language Models (LLMs) has been shown to improve accuracy on reasoning tasks and continues to attract significant attention. Existing RLVR methods, however, typically treat all tokens uniformly without accounting for token-level advantages. These methods primarily evaluate performance based on final answer correctness or Pass@K accuracy, and yet make claims about RL post-training leading to improved reasoning traces. This motivates our investigation into the effect of RL post-training on intermediate tokens which are not directly incentivized. To study this, we design an experimental setup using the GRPO algorithm with Qwen-2.5-0.5B model on the GSM8K dataset. We introduce trace coherence, a First-Order Logic (FOL)-based measure to capture the consistency of reasoning steps by identifying errors in the traces. We distinguish between trace validity and trace coherence, noting that the former implies logical soundness while the latter measures local coherence via lack of errors. Our results show that RL post-training overall improves trace coherence with the most significant gains on problems where the base model fails but the RL model succeeds. Surprisingly, RL enhances local coherence without necessarily producing valid or correct solutions. This highlights a crucial distinction: improved local coherence in reasoning steps does not guarantee final answer correctness. We argue that claims of improved reasoning via RL must be examined with care, as these may be based on improved trace coherence, which may not translate into fully valid mathematical proofs.

---

### Moneyball with LLMs: Analyzing Tabular Summarization in Sports Narratives

Authors: Ritam Upadhyay, Naman Ahuja, Rishabh Baral, Aparna Garimella, Vivek Gupta
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.18173v2

Large language model (LLM) approaches to tabular summarization rely on extensive prompt engineering, decomposition pipelines, or entity-level intermediate representations to achieve strong performance. While effective, these strategies are computationally expensive and offer limited insight into how well models maintain state over long, evolving narratives. We introduce SPORTABSET, a diagnostic benchmark for long-context tabular summarization across two complementary sports domains that require tracking multiple entities and aggregating statistics under domain-specific rules. Using SporTabSet, we systematically evaluate decomposition-based strategies across several long context LLMs. Results show that although decomposition substantially improves accuracy and numerical fidelity, gains stem mainly from dissecting multi-entity interference rather than improved local arithmetic. Robustness experiments further reveal high sensitivity to surface-level cues with structured failures, including hallucination, omission, and role confusion. Together, these findings identify consistent multientity memory as a key bottleneck in long context table generation, motivating diagnostic evaluation as a prerequisite for scalable, efficient and reliable tabular summarization models.

---

### Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset

Authors: Clementine Grethen, Simone Gasparini, Geraldine Morin, Jeremy Lebreton, Lucas Marti, Manuel Sanchez-Gestido
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.18172v1

Accurate 3D reconstruction of lunar surfaces is essential for space exploration. However, existing stereo vision reconstruction methods struggle in this context due to the Moon's lack of texture, difficult lighting variations, and atypical orbital trajectories. State-of-the-art deep learning models, trained on human-scale datasets, have rarely been tested on planetary imagery and cannot be transferred directly to lunar conditions. To address this issue, we introduce LunarStereo, the first open dataset of photorealistic stereo image pairs of the Moon, simulated using ray tracing based on high-resolution topography and reflectance models. It covers diverse altitudes, lighting conditions, and viewing angles around the lunar South Pole, offering physically grounded supervision for 3D reconstruction tasks. Based on this dataset, we adapt the MASt3R model to the lunar domain through fine-tuning on LunarStereo. We validate our approach through extensive qualitative and quantitative experiments on both synthetic and real lunar data, evaluating 3D surface reconstruction and relative pose estimation. Extensive experiments on synthetic and real lunar data validate the approach, demonstrating significant improvements over zero-shot baselines and paving the way for robust cross-scale generalization in extraterrestrial environments.

---

### AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI

Authors: Manik Rana, Calissa Man, Anotida Expected Msiiwa, Jeffrey Paine, Kevin Zhu, Sunishchal Dev, Vasu Sharma, Ahan M R
Published: 2025-10-20
Categories: cs.AI, cs.ET, cs.LG, cs.SE, math.OC
arXiv: https://arxiv.org/abs/2510.18170v1

Goal changes are a defining feature of real world multi-turn interactions, yet current agent benchmarks primarily evaluate static objectives or one-shot tool use. We introduce AgentChangeBench, a benchmark explicitly designed to measure how tool augmented language model agents adapt to mid dialogue goal shifts across three enterprise domains. Our framework formalizes evaluation through four complementary metrics: Task Success Rate (TSR) for effectiveness, Tool Use Efficiency (TUE) for reliability, Tool Call Redundancy Rate (TCRR) for wasted effort, and Goal-Shift Recovery Time (GSRT) for adaptation latency. AgentChangeBench comprises 2,835 task sequences and five user personas, each designed to trigger realistic shift points in ongoing workflows. Using this setup, we evaluate several frontier models and uncover sharp contrasts obscured by traditional $\text{pass}@k$ scores: for example, GPT-4o reaches $92.2\%$ recovery on airline booking shifts while Gemini collapses to $48.6\%$, and retail tasks show near perfect parameter validity yet redundancy rates above $80\%$, revealing major inefficiencies. These findings demonstrate that high raw accuracy does not imply robustness under dynamic goals, and that explicit measurement of recovery time and redundancy is essential. AgentChangeBench establishes a reproducible testbed for diagnosing and improving agent resilience in realistic enterprise settings.

---

### Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model

Authors: Yihong Dong, Zhaoyu Ma, Xue Jiang, Zhiyuan Fan, Jiaru Qian, Yongmin Li, Jianha Xiao, Zhi Jin, Rongyu Cao, Binhua Li, Fei Huang, Yongbin Li et al.
Published: 2025-10-20
Categories: cs.AI, cs.CL, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2510.18165v3

Diffusion language models (DLMs) are emerging as a compelling alternative to the dominant autoregressive paradigm, offering inherent advantages in parallel generation and bidirectional context modeling. However, for the tasks with strict structural constraints such as code generation, DLMs face a critical trade-off between inference speed and output quality, where accelerating generation by reducing sampling steps often leads to catastrophic performance collapse. We find that the fundamental reasons are: 1) the generation difficulty is non-uniform in the structured sequence decoding steps, making DLM's static acceleration strategy suboptimal; 2) the context of tokens generated by DLM evolves continuously, causing early high-confidence predictions to turn into irreversible errors. In this paper, we introduce efficient Sampling with Adaptive acceleration and Backtracking Enhanced Remasking (i.e., Saber), a novel training-free sampling algorithm for DLMs that first achieves both better inference speed and output quality in code generation. Saber dynamically adjusts the number of tokens unmasked per step based on the model's evolving confidence, and utilizes a backtracking mechanism to revert tokens whose confidence drops as new context emerges, with its effectiveness supported by theoretical analysis. Extensive experiments on multiple mainstream code generation benchmarks show that Saber boosts Pass@1 accuracy by an average of 1.9\% over mainstream DLM sampling methods, while achieving an average 251.4\% inference speedup. By leveraging the inherent advantages of DLMs, our work significantly narrows the performance gap with autoregressive models in code generation.

---

### Automatic Prompt Generation via Adaptive Selection of Prompting Techniques

Authors: Yohei Ikenoue, Hitomi Tashiro, Shigeru Kuroyanagi
Published: 2025-10-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.18162v1

Prompt engineering is crucial for achieving reliable and effective outputs from large language models (LLMs), but its design requires specialized knowledge of prompting techniques and a deep understanding of target tasks. To address this challenge, we propose a novel method that adaptively selects task-appropriate prompting techniques based on users' abstract task descriptions and automatically generates high-quality prompts without relying on pre-existing templates or frameworks. The proposed method constructs a knowledge base that associates task clusters, characterized by semantic similarity across diverse tasks, with their corresponding prompting techniques. When users input task descriptions, the system assigns them to the most relevant task cluster and dynamically generates prompts by integrating techniques drawn from the knowledge base. An experimental evaluation of the proposed method on 23 tasks from BIG-Bench Extra Hard (BBEH) demonstrates superior performance compared with standard prompts and existing automatic prompt-generation tools, as measured by both arithmetic and harmonic mean scores. This research establishes a foundation for streamlining and standardizing prompt creation, enabling non-experts to effectively leverage LLMs.

---

### Beating the Winner's Curse via Inference-Aware Policy Optimization

Authors: Hamsa Bastani, Osbert Bastani, Bryce McLaughlin
Published: 2025-10-20
Categories: stat.ML, cs.LG, econ.EM
arXiv: https://arxiv.org/abs/2510.18161v3

There has been a surge of recent interest in automatically learning policies to target treatment decisions based on rich individual covariates. In addition, practitioners want confidence that the learned policy has better performance than the incumbent policy according to downstream policy evaluation. However, due to the winner's curse -- an issue where the policy optimization procedure exploits prediction errors rather than finding actual improvements -- predicted performance improvements are often not substantiated by downstream policy evaluation. To address this challenge, we propose a novel strategy called inference-aware policy optimization, which modifies policy optimization to account for how the policy will be evaluated downstream. Specifically, it optimizes not only for the estimated objective value, but also for the chances that the estimate of the policy's improvement passes a significance test during downstream policy evaluation. We mathematically characterize the Pareto frontier of policies according to the tradeoff of these two goals. Based on our characterization, we design a policy optimization algorithm that estimates the Pareto frontier using machine learning models; then, the decision-maker can select the policy that optimizes their desired tradeoff, after which policy evaluation can be performed on the test set as usual. Finally, we perform simulations to illustrate the effectiveness of our methodology.

---

### LLM-Based Multi-Agent System for Simulating and Analyzing Marketing and Consumer Behavior

Authors: Man-Lin Chu, Lucian Terhorst, Kadin Reed, Tom Ni, Weiwei Chen, Rongyu Lin
Published: 2025-10-20
Categories: cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2510.18155v1

Simulating consumer decision-making is vital for designing and evaluating marketing strategies before costly real-world deployment. However, post-event analyses and rule-based agent-based models (ABMs) struggle to capture the complexity of human behavior and social interaction. We introduce an LLM-powered multi-agent simulation framework that models consumer decisions and social dynamics. Building on recent advances in large language model simulation in a sandbox environment, our framework enables generative agents to interact, express internal reasoning, form habits, and make purchasing decisions without predefined rules. In a price-discount marketing scenario, the system delivers actionable strategy-testing outcomes and reveals emergent social patterns beyond the reach of conventional methods. This approach offers marketers a scalable, low-risk tool for pre-implementation testing, reducing reliance on time-intensive post-event evaluations and lowering the risk of underperforming campaigns.

---

### Annotating the Chain-of-Thought: A Behavior-Labeled Dataset for AI Safety

Authors: Antonio-Gabriel Chacón Menke, Phan Xuan Tan, Eiji Kamioka
Published: 2025-10-20
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2510.18154v1

Recent work has highlighted the importance of monitoring chain-of-thought reasoning for AI safety; however, current approaches that analyze textual reasoning steps can miss subtle harmful patterns and may be circumvented by models that hide unsafe reasoning. We present a sentence-level labeled dataset that enables activation-based monitoring of safety behaviors during LLM reasoning. Our dataset contains reasoning sequences with sentence-level annotations of safety behaviors such as expression of safety concerns or speculation on user intent, which we use to extract steering vectors for detecting and influencing these behaviors within model activations. The dataset fills a key gap in safety research: while existing datasets label reasoning holistically, effective application of steering vectors for safety monitoring could be improved by identifying precisely when specific behaviors occur within reasoning chains. We demonstrate the dataset's utility by extracting representations that both detect and steer safety behaviors in model activations, showcasing the potential of activation-level techniques for improving safety oversight on reasoning. Content Warning: This paper discusses AI safety in the context of harmful prompts and may contain references to potentially harmful content.

---

### Extracting Rule-based Descriptions of Attention Features in Transformers

Authors: Dan Friedman, Adithya Bhaskar, Alexander Wettig, Danqi Chen
Published: 2025-10-20
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.18148v1

Mechanistic interpretability strives to explain model behavior in terms of bottom-up primitives. The leading paradigm is to express hidden states as a sparse linear combination of basis vectors, called features. However, this only identifies which text sequences (exemplars) activate which features; the actual interpretation of features requires subjective inspection of these exemplars. This paper advocates for a different solution: rule-based descriptions that match token patterns in the input and correspondingly increase or decrease the likelihood of specific output tokens. Specifically, we extract rule-based descriptions of SAE features trained on the outputs of attention layers. While prior work treats the attention layers as an opaque box, we describe how it may naturally be expressed in terms of interactions between input and output features, of which we study three types: (1) skip-gram rules of the form "(Canadian city)... speaks --> English", (2) absence rules of the form "(Montreal)... speaks -/-> English," and (3) counting rules that toggle only when the count of a word exceeds a certain value or the count of another word. Absence and counting rules are not readily discovered by inspection of exemplars, where manual and automatic descriptions often identify misleading or incomplete explanations. We then describe a simple approach to extract these types of rules automatically from a transformer, and apply it to GPT-2 small. We find that a majority of features may be described well with around 100 skip-gram rules, though absence rules are abundant even as early as the first layer (in over a fourth of features). We also isolate a few examples of counting rules. This paper lays the groundwork for future research into rule-based descriptions of features by defining them, showing how they may be extracted, and providing a preliminary taxonomy of some of the behaviors they represent.

---

### LLMs Encode How Difficult Problems Are

Authors: William Lugoloobi, Chris Russell
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.18147v1

Large language models exhibit a puzzling inconsistency: they solve complex problems yet frequently fail on seemingly simpler ones. We investigate whether LLMs internally encode problem difficulty in a way that aligns with human judgment, and whether this representation tracks generalization during reinforcement learning post-training. We train linear probes across layers and token positions on 60 models, evaluating on mathematical and coding subsets of Easy2HardBench. We find that human-labeled difficulty is strongly linearly decodable (AMC: $ρ\approx 0.88$) and exhibits clear model-size scaling, whereas LLM-derived difficulty is substantially weaker and scales poorly. Steering along the difficulty direction reveals that pushing models toward "easier" representations reduces hallucination and improves accuracy. During GRPO training on Qwen2.5-Math-1.5B, the human-difficulty probe strengthens and positively correlates with test accuracy across training steps, while the LLM-difficulty probe degrades and negatively correlates with performance. These results suggest that human annotations provide a stable difficulty signal that RL amplifies, while automated difficulty estimates derived from model performance become misaligned precisely as models improve. We release probe code and evaluation scripts to facilitate replication.

---

### Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models

Authors: Huan Song, Deeksha Razdan, Yiyue Qian, Arijit Ghosh Chowdhury, Parth Patwa, Aman Chadha, Shinan Zhang, Sharlina Keshava, Hannah Marlowe
Published: 2025-10-20
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.18143v1

Small Language Models (SLMs) offer compelling advantages in deployment cost and latency, but their accuracy often lags behind larger models, particularly for complex domain-specific tasks. While supervised fine-tuning can help bridge this performance gap, it requires substantial manual effort in data preparation and iterative optimization. We present PaDA-Agent (Pattern-guided Data Augmentation Agent), an evaluation-driven approach that streamlines the data augmentation process for SLMs through coordinated operations. Unlike state-of-the-art approaches that focus on model training errors only and generating error-correcting samples, PaDA-Agent discovers failure patterns from the validation data via evaluations and drafts targeted data augmentation strategies aiming to directly reduce the generalization gap. Our experimental results demonstrate significant improvements over state-of-the-art LLM-based data augmentation approaches for Llama 3.2 1B Instruct model fine-tuning.

---

### World-in-World: World Models in a Closed-Loop World

Authors: Jiahan Zhang, Muqing Jiang, Nanru Dai, Taiming Lu, Arda Uzunoglu, Shunchi Zhang, Yana Wei, Jiahao Wang, Vishal M. Patel, Paul Pu Liang, Daniel Khashabi, Cheng Peng et al.
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.18135v2

Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchmarks adopt open-loop protocols that emphasize visual quality in isolation, leaving the core issue of embodied utility unresolved, i.e., do WMs actually help agents succeed at embodied tasks? To address this gap, we introduce World-in-World, the first open platform that benchmarks WMs in a closed-loop world that mirrors real agent-environment interactions. World-in-World provides a unified online planning strategy and a standardized action API, enabling heterogeneous WMs for decision making. We curate four closed-loop environments that rigorously evaluate diverse WMs, prioritize task success as the primary metric, and move beyond the common focus on visual quality; we also present the first data scaling law for world models in embodied settings. Our study uncovers three surprises: (1) visual quality alone does not guarantee task success, controllability matters more; (2) scaling post-training with action-observation data is more effective than upgrading the pretrained video generators; and (3) allocating more inference-time compute allows WMs to substantially improve closed-loop performance.

---

### Evaluating LLM Reasoning Beyond Correctness and CoT

Authors: Soheil Abbasloo
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.18134v2

What does it truly mean for a language model to "reason"? Current evaluations reward models' correct standalone answers-but correctness alone reveals little about the process that produced them. We argue that reasoning should be understood not as a static chain of steps but as a dynamic trajectory in which ideas interact, clash, and evolve into integrated insights. Building on the philosophical tradition of dialectics, we introduce SIEV, a structured evaluation framework that assesses reasoning through explicit thesis-antithesis-synthesis interactions. SIEV produces interpretable trajectories that highlight key properties of reasoning-robustness to challenge, adaptability under conflict, and synthesis across competing viewpoints-dimensions that conventional correctness-based metrics cannot capture. Empirical results on GSM and MMLU demonstrate substantial gaps in the reasoning abilities of state-of-the-art models: for example, GPT-5-chat loses more than 40 points (out of 100) on GSM when evaluated through SIEV's process-oriented lens. By shifting focus from what answer a model gives to how it arrives there, SIEV enables a more transparent and principled distinction between structured reasoning and surface-level pattern generation offering a clearer foundation for assessing and understanding the reasoning capabilities of LLMs.

---

### Rethinking PCA Through Duality

Authors: Jan Quan, Johan Suykens, Panagiotis Patrinos
Published: 2025-10-20
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2510.18130v1

Motivated by the recently shown connection between self-attention and (kernel) principal component analysis (PCA), we revisit the fundamentals of PCA. Using the difference-of-convex (DC) framework, we present several novel formulations and provide new theoretical insights. In particular, we show the kernelizability and out-of-sample applicability for a PCA-like family of problems. Moreover, we uncover that simultaneous iteration, which is connected to the classical QR algorithm, is an instance of the difference-of-convex algorithm (DCA), offering an optimization perspective on this longstanding method. Further, we describe new algorithms for PCA and empirically compare them with state-of-the-art methods. Lastly, we introduce a kernelizable dual formulation for a robust variant of PCA that minimizes the $l_1$ deviation of the reconstruction errors.

---

### SafeCoop: Unravelling Full Stack Safety in Agentic Collaborative Driving

Authors: Xiangbo Gao, Tzu-Hsiang Lin, Ruojing Song, Yuheng Wu, Kuan-Ru Huang, Zicheng Jin, Fangzhou Lin, Shinan Liu, Zhengzhong Tu
Published: 2025-10-20
Categories: cs.CV, cs.AI, cs.CL, cs.RO
arXiv: https://arxiv.org/abs/2510.18123v1

Collaborative driving systems leverage vehicle-to-everything (V2X) communication across multiple agents to enhance driving safety and efficiency. Traditional V2X systems take raw sensor data, neural features, or perception results as communication media, which face persistent challenges, including high bandwidth demands, semantic loss, and interoperability issues. Recent advances investigate natural language as a promising medium, which can provide semantic richness, decision-level reasoning, and human-machine interoperability at significantly lower bandwidth. Despite great promise, this paradigm shift also introduces new vulnerabilities within language communication, including message loss, hallucinations, semantic manipulation, and adversarial attacks. In this work, we present the first systematic study of full-stack safety and security issues in natural-language-based collaborative driving. Specifically, we develop a comprehensive taxonomy of attack strategies, including connection disruption, relay/replay interference, content spoofing, and multi-connection forgery. To mitigate these risks, we introduce an agentic defense pipeline, which we call SafeCoop, that integrates a semantic firewall, language-perception consistency checks, and multi-source consensus, enabled by an agentic transformation function for cross-frame spatial alignment. We systematically evaluate SafeCoop in closed-loop CARLA simulation across 32 critical scenarios, achieving 69.15% driving score improvement under malicious attacks and up to 67.32% F1 score for malicious detection. This study provides guidance for advancing research on safe, secure, and trustworthy language-driven collaboration in transportation systems. Our project page is https://xiangbogaobarry.github.io/SafeCoop.

---

### HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fields

Authors: Sudarshan Babu, Phillip Lo, Xiao Zhang, Aadi Srivastava, Ali Davariashtiyani, Jason Perera, Michael Maire, Aly A. Khan
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.18122v1

We introduce HyperDiffusionFields (HyDiF), a framework that models 3D molecular conformers as continuous fields rather than discrete atomic coordinates or graphs. At the core of our approach is the Molecular Directional Field (MDF), a vector field that maps any point in space to the direction of the nearest atom of a particular type. We represent MDFs using molecule-specific neural implicit fields, which we call Molecular Neural Fields (MNFs). To enable learning across molecules and facilitate generalization, we adopt an approach where a shared hypernetwork, conditioned on a molecule, generates the weights of the given molecule's MNF. To endow the model with generative capabilities, we train the hypernetwork as a denoising diffusion model, enabling sampling in the function space of molecular fields. Our design naturally extends to a masked diffusion mechanism to support structure-conditioned generation tasks, such as molecular inpainting, by selectively noising regions of the field. Beyond generation, the localized and continuous nature of MDFs enables spatially fine-grained feature extraction for molecular property prediction, something not easily achievable with graph or point cloud based methods. Furthermore, we demonstrate that our approach scales to larger biomolecules, illustrating a promising direction for field-based molecular modeling.

---

### Efficient Long-context Language Model Training by Core Attention Disaggregation

Authors: Yonghao Zhuang, Junda Chen, Bo Pang, Yi Gu, Yibo Zhu, Yimin Jiang, Ion Stoica, Eric Xing, Hao Zhang
Published: 2025-10-20
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2510.18121v1

We present core attention disaggregation (CAD), a technique that improves long-context large language model training by decoupling the core attention computation, softmax(QK^T)V, from the rest of the model and executing it on a separate pool of devices. In existing systems, core attention is colocated with other layers; at long context lengths, its quadratic compute growth compared to the near-linear growth of other components causes load imbalance and stragglers across data and pipeline parallel groups. CAD is enabled by two observations. First, core attention is stateless: it has no trainable parameters and only minimal transient data, so balancing reduces to scheduling compute-bound tasks. Second, it is composable: modern attention kernels retain high efficiency when processing fused batches of token-level shards with arbitrary lengths. CAD partitions core attention into token-level tasks and dispatches them to dedicated attention servers, which dynamically rebatch tasks to equalize compute without sacrificing kernel efficiency. We implement CAD in a system called DistCA, which uses a ping-pong execution scheme to fully overlap communication with computation and in-place execution on attention servers to reduce memory use. On 512 H200 GPUs and context lengths up to 512k tokens, DistCA improves end-to-end training throughput by up to 1.35x, eliminates data and pipeline parallel stragglers, and achieves near-perfect compute and memory balance.

---

### Generalization Below the Edge of Stability: The Role of Data Geometry

Authors: Tongtong Liang, Alexander Cloninger, Rahul Parhi, Yu-Xiang Wang
Published: 2025-10-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.18120v3

Understanding generalization in overparameterized neural networks hinges on the interplay between the data geometry, neural architecture, and training dynamics. In this paper, we theoretically explore how data geometry controls this implicit bias. This paper presents theoretical results for overparametrized two-layer ReLU networks trained below the edge of stability. First, for data distributions supported on a mixture of low-dimensional balls, we derive generalization bounds that provably adapt to the intrinsic dimension. Second, for a family of isotropic distributions that vary in how strongly probability mass concentrates toward the unit sphere, we derive a spectrum of bounds showing that rates deteriorate as the mass concentrates toward the sphere. These results instantiate a unifying principle: When the data is harder to "shatter" with respect to the activation thresholds of the ReLU neurons, gradient descent tends to learn representations that capture shared patterns and thus finds solutions that generalize well. On the other hand, for data that is easily shattered (e.g., data supported on the sphere) gradient descent favors memorization. Our theoretical results consolidate disparate empirical findings that have appeared in the literature.

---

### Gradient Variance Reveals Failure Modes in Flow-Based Generative Models

Authors: Teodora Reu, Sixtine Dromigny, Michael Bronstein, Francisco Vargas
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.18118v1

Rectified Flows learn ODE vector fields whose trajectories are straight between source and target distributions, enabling near one-step inference. We show that this straight-path objective conceals fundamental failure modes: under deterministic training, low gradient variance drives memorization of arbitrary training pairings, even when interpolant lines between pairs intersect. To analyze this mechanism, we study Gaussian-to-Gaussian transport and use the loss gradient variance across stochastic and deterministic regimes to characterize which vector fields optimization favors in each setting. We then show that, in a setting where all interpolating lines intersect, applying Rectified Flow yields the same specific pairings at inference as during training. More generally, we prove that a memorizing vector field exists even when training interpolants intersect, and that optimizing the straight-path objective converges to this ill-defined field. At inference, deterministic integration reproduces the exact training pairings. We validate our findings empirically on the CelebA dataset, confirming that deterministic interpolants induce memorization, while the injection of small noise restores generalization.

---

### Online In-Context Distillation for Low-Resource Vision Language Models

Authors: Zhiqi Kang, Rahaf Aljundi, Vaggelis Dorovatas, Karteek Alahari
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.18117v2

As the field continues its push for ever more resources, this work turns the spotlight on a critical question: how can vision-language models (VLMs) be adapted to thrive in low-resource, budget-constrained settings? While large VLMs offer strong performance, they are impractical to deploy in such settings. Small VLMs, on the other hand, are efficient but typically require costly fine-tuning to close the performance gap with larger models in the deployment domain. Inspired by the in-context learning framework, we propose an online In-Context Distillation (ICD) method, in which a small VLM collaborates with a stronger teacher model at inference time, distilling its knowledge via sparse demonstrations to efficiently bridge the gap between them. Our method is built on an in-depth analysis that identifies the scale and the choice of models for which vision-language ICL is currently feasible, and demonstrates the advantage of ICL over fine-tuning under constrained compute budgets. We enhance our method with a novel cross-modal demonstration selection strategy, teacher test-time scaling to reduce noise, and student uncertainty conditioning to dynamically populate a demonstration pool and minimize teacher queries. Our ICD method significantly boosts the performance of small models (up to 33%) using scarce teacher annotations (as low as 4%), and competes with the teacher's zero-shot performance.

---

### Latent-Augmented Discrete Diffusion Models

Authors: Dario Shariatian, Alain Durmus, Umut Simsekli, Stefano Peluchetti
Published: 2025-10-20
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2510.18114v3

Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions ignoring cross-token dependencies and degrading few-step performance. We propose Latent-Augmented Discrete Diffusion (LADD), which introduces a learnable auxiliary latent channel and performs diffusion over the joint (token, latent) space. The latent variables provide an intermediate representation expressing joint structure while preserving tractable parameterizations. We instantiate LADD with continuous latents (Co-LADD) and discrete latents (Di-LADD), and study two inference schedules: a joint diffusion that denoises data and latents together, and a sequential diffusion that first resolves latents and then samples tokens conditionally. We derive ELBO-style objectives and analyze design choices that balance latent expressivity with diffusion compatibility. In experiments, LADD models yield improvements on unconditional generation metrics as compared to state-of-the-art masked discrete diffusion baselines, and are effective at lower sampling budgets, where unmasking many tokens per step is desirable.

---

### Does Reasoning Help LLM Agents Play Dungeons and Dragons? A Prompt Engineering Experiment

Authors: Patricia Delafuente, Arya Honraopatil, Lara J. Martin
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.18112v1

This paper explores the application of Large Language Models (LLMs) and reasoning to predict Dungeons & Dragons (DnD) player actions and format them as Avrae Discord bot commands. Using the FIREBALL dataset, we evaluated a reasoning model, DeepSeek-R1-Distill-LLaMA-8B, and an instruct model, LLaMA-3.1-8B-Instruct, for command generation. Our findings highlight the importance of providing specific instructions to models, that even single sentence changes in prompts can greatly affect the output of models, and that instruct models are sufficient for this task compared to reasoning models.

---

### PrivaDE: Privacy-preserving Data Evaluation for Blockchain-based Data Marketplaces

Authors: Wan Ki Wong, Sahel Torkamani, Michele Ciampi, Rik Sarkar
Published: 2025-10-20
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2510.18109v4

Evaluating the usefulness of data before purchase is essential when obtaining data for high-quality machine learning models, yet both model builders and data providers are often unwilling to reveal their proprietary assets. We present PrivaDE, a privacy-preserving protocol that allows a model owner and a data owner to jointly compute a utility score for a candidate dataset without fully exposing model parameters, raw features, or labels. PrivaDE provides strong security against malicious behavior and can be integrated into blockchain-based marketplaces, where smart contracts enforce fair execution and payment. To make the protocol practical, we propose optimizations to enable efficient secure model inference, and a model-agnostic scoring method that uses only a small, representative subset of the data while still reflecting its impact on downstream training. Evaluation shows that PrivaDE performs data evaluation effectively, achieving online runtimes within 15 minutes even for models with millions of parameters. Our work lays the foundation for fair and automated data marketplaces in decentralized machine learning ecosystems.

---

### Na Prática, qual IA Entende o Direito? Um Estudo Experimental com IAs Generalistas e uma IA Jurídica

Authors: Marina Soares Marinho, Daniela Vianna, Livy Real, Altigran da Silva, Gabriela Migliorini
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.18108v1

This study presents the Jusbrasil Study on the Use of General-Purpose AIs in Law, proposing an experimental evaluation protocol combining legal theory, such as material correctness, systematic coherence, and argumentative integrity, with empirical assessment by 48 legal professionals. Four systems (JusIA, ChatGPT Free, ChatGPT Pro, and Gemini) were tested in tasks simulating lawyers' daily work. JusIA, a domain-specialized model, consistently outperformed the general-purpose systems, showing that both domain specialization and a theoretically grounded evaluation are essential for reliable legal AI outputs.

---

### From AutoRecSys to AutoRecLab: A Call to Build, Evaluate, and Govern Autonomous Recommender-Systems Research Labs

Authors: Joeran Beel, Bela Gipp, Tobias Vente, Moritz Baumgart, Philipp Meister
Published: 2025-10-20
Categories: cs.IR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.18104v1

Recommender-systems research has accelerated model and evaluation advances, yet largely neglects automating the research process itself. We argue for a shift from narrow AutoRecSys tools -- focused on algorithm selection and hyper-parameter tuning -- to an Autonomous Recommender-Systems Research Lab (AutoRecLab) that integrates end-to-end automation: problem ideation, literature analysis, experimental design and execution, result interpretation, manuscript drafting, and provenance logging. Drawing on recent progress in automated science (e.g., multi-agent AI Scientist and AI Co-Scientist systems), we outline an agenda for the RecSys community: (1) build open AutoRecLab prototypes that combine LLM-driven ideation and reporting with automated experimentation; (2) establish benchmarks and competitions that evaluate agents on producing reproducible RecSys findings with minimal human input; (3) create review venues for transparently AI-generated submissions; (4) define standards for attribution and reproducibility via detailed research logs and metadata; and (5) foster interdisciplinary dialogue on ethics, governance, privacy, and fairness in autonomous research. Advancing this agenda can increase research throughput, surface non-obvious insights, and position RecSys to contribute to emerging Artificial Research Intelligence. We conclude with a call to organise a community retreat to coordinate next steps and co-author guidance for the responsible integration of automated research systems.

---

### Enhancing mortality prediction in cardiac arrest ICU patients through meta-modeling of structured clinical data from MIMIC-IV

Authors: Nursultan Mamatov, Philipp Kellmeyer
Published: 2025-10-20
Categories: cs.LG, cs.AI, q-bio.QM
arXiv: https://arxiv.org/abs/2510.18103v1

Accurate early prediction of in-hospital mortality in intensive care units (ICUs) is essential for timely clinical intervention and efficient resource allocation. This study develops and evaluates machine learning models that integrate both structured clinical data and unstructured textual information, specifically discharge summaries and radiology reports, from the MIMIC-IV database. We used LASSO and XGBoost for feature selection, followed by a multivariate logistic regression trained on the top features identified by both models. Incorporating textual features using TF-IDF and BERT embeddings significantly improved predictive performance. The final logistic regression model, which combined structured and textual input, achieved an AUC of 0.918, compared to 0.753 when using structured data alone, a relative improvement 22%. The analysis of the decision curve demonstrated a superior standardized net benefit in a wide range of threshold probabilities (0.2-0.8), confirming the clinical utility of the model. These results underscore the added prognostic value of unstructured clinical notes and support their integration into interpretable feature-driven risk prediction models for ICU patients.

---

### From Volume Rendering to 3D Gaussian Splatting: Theory and Applications

Authors: Vitor Pereira Matias, Daniel Perazzo, Vinicius Silva, Alberto Raposo, Luiz Velho, Afonso Paiva, Tiago Novello
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.18101v1

The problem of 3D reconstruction from posed images is undergoing a fundamental transformation, driven by continuous advances in 3D Gaussian Splatting (3DGS). By modeling scenes explicitly as collections of 3D Gaussians, 3DGS enables efficient rasterization through volumetric splatting, offering thus a seamless integration with common graphics pipelines. Despite its real-time rendering capabilities for novel view synthesis, 3DGS suffers from a high memory footprint, the tendency to bake lighting effects directly into its representation, and limited support for secondary-ray effects. This tutorial provides a concise yet comprehensive overview of the 3DGS pipeline, starting from its splatting formulation and then exploring the main efforts in addressing its limitations. Finally, we survey a range of applications that leverage 3DGS for surface reconstruction, avatar modeling, animation, and content generation-highlighting its efficient rendering and suitability for feed-forward pipelines.

---

### SMaRT: Select, Mix, and ReinvenT -- A Strategy Fusion Framework for LLM-Driven Reasoning and Planning

Authors: Nikhil Verma, Manasa Bharadwaj, Wonjun Jang, Harmanpreet Singh, Yixiao Wang, Homa Fashandi, Chul Lee
Published: 2025-10-20
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.18095v2

Large Language Models (LLMs) have redefined complex task automation with exceptional generalization capabilities. Despite these advancements, state-of-the-art methods rely on single-strategy prompting, missing the synergy of diverse reasoning approaches. No single strategy excels universally, highlighting the need for frameworks that fuse strategies to maximize performance and ensure robustness. We introduce the Select, Mix, and ReinvenT (SMaRT) framework, an innovative strategy fusion approach designed to overcome this constraint by creating balanced and efficient solutions through the seamless integration of diverse reasoning strategies. Unlike existing methods, which employ LLMs merely as evaluators, SMaRT uses them as intelligent integrators, unlocking the "best of all worlds" across tasks. Extensive empirical evaluations across benchmarks in reasoning, planning, and sequential decision-making highlight the robustness and adaptability of SMaRT. The framework consistently outperforms state-of-the-art baselines in solution quality, constraint adherence, and performance metrics. This work redefines LLM-driven decision-making by pioneering a new paradigm in cross-strategy calibration, unlocking superior outcomes for reasoning systems and advancing the boundaries of self-refining methodologies.

---

### Accelerating Vision Transformers with Adaptive Patch Sizes

Authors: Rohan Choudhury, JungEun Kim, Jinhyung Park, Eunho Yang, László A. Jeni, Kris M. Kitani
Published: 2025-10-20
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.18091v2

Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We present Adaptive Patch Transformers (APT), which addresses this by using multiple different patch sizes within the same image. APT reduces the total number of input tokens by allocating larger patch sizes in more homogeneous areas and smaller patches in more complex ones. APT achieves a drastic speedup in ViT inference and training, increasing throughput by 40% on ViT-L and 50% on ViT-H while maintaining downstream performance, and can be applied to a previously fine-tuned ViT, converging in as little as 1 epoch. It also significantly reduces training and inference time without loss of performance in high-resolution dense visual tasks, achieving up to 30\% faster training and inference in visual QA, object detection, and semantic segmentation.

---

### Big Data, Tiny Targets: An Exploratory Study in Machine Learning-enhanced Detection of Microplastic from Filters

Authors: Paul-Tiberiu Miclea, Martin Sboron, Hardik Vaghasiya, Hoang Thinh Nguyen, Meet Gadara, Thomas Schmid
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.18089v1

Microplastics (MPs) are ubiquitous pollutants with demonstrated potential to impact ecosystems and human health. Their microscopic size complicates detection, classification, and removal, especially in biological and environmental samples. While techniques like optical microscopy, Scanning Electron Microscopy (SEM), and Atomic Force Microscopy (AFM) provide a sound basis for detection, applying these approaches requires usually manual analysis and prevents efficient use in large screening studies. To this end, machine learning (ML) has emerged as a powerful tool in advancing microplastic detection. In this exploratory study, we investigate potential, limitations and future directions of advancing the detection and quantification of MP particles and fibres using a combination of SEM imaging and machine learning-based object detection. For simplicity, we focus on a filtration scenario where image backgrounds exhibit a symmetric and repetitive pattern. Our findings indicate differences in the quality of YOLO models for the given task and the relevance of optimizing preprocessing. At the same time, we identify open challenges, such as limited amounts of expert-labeled data necessary for reliable training of ML models.

---

### Planned Diffusion

Authors: Daniel Israel, Tian Jin, Ellie Cheng, Guy Van den Broeck, Aditya Grover, Suvinay Subramanian, Michael Carbin
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.18087v2

Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strategy for deciding which tokens to decode at each step. Determining a good denoising order is difficult, and existing approaches use heuristics that create a steep trade-off between quality and latency. We propose planned diffusion, a system that trains the model to determine its own denoising order. Planned diffusion uses a single model that transitions between autoregressive and diffusion-based generation: first, the model autoregressively generates a plan that partitions the response into semantically independent chunks; second, the model denoises all chunks in parallel. The autoregressive plan enables the model to define the denoising order itself. On AlpacaEval, planned diffusion achieves 1.27x to 1.81x speedup over autoregressive generation with only 0.87% to 5.4% drop in win rate, establishing a new Pareto frontier for parallel generation with discrete diffusion. Additionally, planned diffusion's instruction following quality continues to improve with more finetuning compute, while the autoregressive baseline plateaus. Our implementation provides simple runtime knobs that offer tunable control over the quality-latency trade-off.

---

### R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations

Authors: Connor Mattson, Varun Raveendra, Ellen Novoseller, Nicholas Waytowich, Vernon J. Lawhern, Daniel S. Brown
Published: 2025-10-20
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.18085v2

Imitation Learning (IL) is a natural way for humans to teach robots, particularly when high-quality demonstrations are easy to obtain. While IL has been widely applied to single-robot settings, relatively few studies have addressed the extension of these methods to multi-agent systems, especially in settings where a single human must provide demonstrations to a team of collaborating robots. In this paper, we introduce and study Round-Robin Behavior Cloning (R2BC), a method that enables a single human operator to effectively train multi-robot systems through sequential, single-agent demonstrations. Our approach allows the human to teleoperate one agent at a time and incrementally teach multi-agent behavior to the entire system, without requiring demonstrations in the joint multi-agent action space. We show that R2BC methods match, and in some cases surpass, the performance of an oracle behavior cloning approach trained on privileged synchronized demonstrations across four multi-agent simulated tasks. Finally, we deploy R2BC on two physical robot tasks trained using real human demonstrations.

---

### RL-Driven Security-Aware Resource Allocation Framework for UAV-Assisted O-RAN

Authors: Zaineh Abughazzah, Emna Baccour, Loay Ismail, Amr Mohamed, Mounir Hamdi
Published: 2025-10-20
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.18084v1

The integration of Unmanned Aerial Vehicles (UAVs) into Open Radio Access Networks (O-RAN) enhances communication in disaster management and Search and Rescue (SAR) operations by ensuring connectivity when infrastructure fails. However, SAR scenarios demand stringent security and low-latency communication, as delays or breaches can compromise mission success. While UAVs serve as mobile relays, they introduce challenges in energy consumption and resource management, necessitating intelligent allocation strategies. Existing UAV-assisted O-RAN approaches often overlook the joint optimization of security, latency, and energy efficiency in dynamic environments. This paper proposes a novel Reinforcement Learning (RL)-based framework for dynamic resource allocation in UAV relays, explicitly addressing these trade-offs. Our approach formulates an optimization problem that integrates security-aware resource allocation, latency minimization, and energy efficiency, which is solved using RL. Unlike heuristic or static methods, our framework adapts in real-time to network dynamics, ensuring robust communication. Simulations demonstrate superior performance compared to heuristic baselines, achieving enhanced security and energy efficiency while maintaining ultra-low latency in SAR scenarios.

---

### Chimera: Compositional Image Generation using Part-based Concepting

Authors: Shivam Singh, Yiming Chen, Agneet Chatterjee, Amit Raj, James Hays, Yezhou Yang, Chitta Baral
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.18083v2

Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.

---

### Provably Optimal Reinforcement Learning under Safety Filtering

Authors: Donggeon David Oh, Duy P. Nguyen, Haimin Hu, Jaime Fernández Fisac
Published: 2025-10-20
Categories: cs.LG, cs.RO, eess.SY
arXiv: https://arxiv.org/abs/2510.18082v3

Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits its application in safety-critical settings. A common practical approach is to augment the RL policy with a safety filter that overrides unsafe actions to prevent failures during both training and deployment. However, safety filtering is often perceived as sacrificing performance and hindering the learning process. We show that this perceived safety-performance tradeoff is not inherent and prove, for the first time, that enforcing safety with a sufficiently permissive safety filter does not degrade asymptotic performance. We formalize RL safety with a safety-critical Markov decision process (SC-MDP), which requires categorical, rather than high-probability, avoidance of catastrophic failure states. Additionally, we define an associated filtered MDP in which all actions result in safe effects, thanks to a safety filter that is considered to be a part of the environment. Our main theorem establishes that (i) learning in the filtered MDP is safe categorically, (ii) standard RL convergence carries over to the filtered MDP, and (iii) any policy that is optimal in the filtered MDP, when executed through the same filter, achieves the same asymptotic return as the best safe policy in the SC-MDP, yielding a complete separation between safety enforcement and performance optimization. We validate the theory on Safety Gymnasium with representative tasks and constraints, observing zero violations during training and final performance matching or exceeding unfiltered baselines. Together, these results shed light on a long-standing question in safety-filtered learning and provide a simple, principled recipe for safe RL: train and deploy RL policies with the most permissive safety filter that is available.

---

### Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth

Authors: Jiawei Zhang, Andrew Estornell, David D. Baek, Bo Li, Xiaojun Xu
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.18081v1

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway (either through the adversarial attacks or via harmful assistant-prefill attacks). This raises a fundamental question: Can the innate shallow alignment in LLMs be unlocked to ensure safety at arbitrary generation depths? To achieve this goal, we propose Any-Depth Alignment (ADA), an effective inference-time defense with negligible overhead. ADA is built based on our observation that alignment is concentrated in the assistant header tokens through repeated use in shallow-refusal training, and these tokens possess the model's strong alignment priors. By reintroducing these tokens mid-stream, ADA induces the model to reassess harmfulness and recover refusals at any point in generation. Across diverse open-source model families (Llama, Gemma, Mistral, Qwen, DeepSeek, and gpt-oss), ADA achieves robust safety performance without requiring any changes to the base model's parameters. It secures a near-100% refusal rate against challenging adversarial prefill attacks ranging from dozens to thousands of tokens. Furthermore, ADA reduces the average success rate of prominent adversarial prompt attacks (such as GCG, AutoDAN, PAIR, and TAP) to below 3%. This is all accomplished while preserving utility on benign tasks with minimal over-refusal. ADA maintains this resilience even after the base model undergoes subsequent instruction tuning (benign or adversarial).

---

### MEG-GPT: A transformer-based foundation model for magnetoencephalography data

Authors: Rukuang Huang, Sungjun Cho, Chetan Gohil, Oiwi Parker Jones, Mark Woolrich
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.18080v1

Modelling the complex spatiotemporal patterns of large-scale brain dynamics is crucial for neuroscience, but traditional methods fail to capture the rich structure in modalities such as magnetoencephalography (MEG). Recent advances in deep learning have enabled significant progress in other domains, such as language and vision, by using foundation models at scale. Here, we introduce MEG-GPT, a transformer based foundation model that uses time-attention and next time-point prediction. To facilitate this, we also introduce a novel data-driven tokeniser for continuous MEG data, which preserves the high temporal resolution of continuous MEG signals without lossy transformations. We trained MEG-GPT on tokenised brain region time-courses extracted from a large-scale MEG dataset (N=612, eyes-closed rest, Cam-CAN data), and show that the learnt model can generate data with realistic spatio-spectral properties, including transient events and population variability. Critically, it performs well in downstream decoding tasks, improving downstream supervised prediction task, showing improved zero-shot generalisation across sessions (improving accuracy from 0.54 to 0.59) and subjects (improving accuracy from 0.41 to 0.49) compared to a baseline methods. Furthermore, we show the model can be efficiently fine-tuned on a smaller labelled dataset to boost performance in cross-subject decoding scenarios. This work establishes a powerful foundation model for electrophysiological data, paving the way for applications in computational neuroscience and neural decoding.

---

### Chain-of-Thought Reasoning Improves Context-Aware Translation with Large Language Models

Authors: Shabnam Ataee, Hugo Huart, Andrei Popescu-Belis
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.18077v2

This paper assesses the ability of large language models (LLMs) to translate texts that include inter-sentential dependencies. We use the English-French DiscEvalMT benchmark (Bawden et al., 2018) with pairs of sentences containing translation challenges for pronominal anaphora and lexical cohesion. We evaluate 12 LLMs from the DeepSeek-R1, GPT, Llama, Mistral and Phi families on two tasks: (1) distinguish a correct translation from a wrong but plausible one; and (2) generate a correct translation. We compare prompts that encourage chain-of-thought reasoning with those that do not. The best models take advantage of reasoning and reach about 90% accuracy on the first task and COMET scores of about 92% on the second task, with GPT-4, GPT-4o and Phi standing out. Moreover, we observe a "wise get wiser" effect: the improvements through reasoning are larger for models that already perform well without reasoning.

---