# Research Papers — 2025-10 · bundle page 124 of 217

> Full-text markdown of papers #6151–6200 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/124
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/123.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/125.md)

### PanoTPS-Net: Panoramic Room Layout Estimation via Thin Plate Spline Transformation

Authors: Hatem Ibrahem, Ahmed Salem, Qinmin Vivian Hu, Guanghui Wang
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11992v1

Accurately estimating the 3D layout of rooms is a crucial task in computer vision, with potential applications in robotics, augmented reality, and interior design. This paper proposes a novel model, PanoTPS-Net, to estimate room layout from a single panorama image. Leveraging a Convolutional Neural Network (CNN) and incorporating a Thin Plate Spline (TPS) spatial transformation, the architecture of PanoTPS-Net is divided into two stages: First, a convolutional neural network extracts the high-level features from the input images, allowing the network to learn the spatial parameters of the TPS transformation. Second, the TPS spatial transformation layer is generated to warp a reference layout to the required layout based on the predicted parameters. This unique combination empowers the model to properly predict room layouts while also generalizing effectively to both cuboid and non-cuboid layouts. Extensive experiments on publicly available datasets and comparisons with state-of-the-art methods demonstrate the effectiveness of the proposed method. The results underscore the model's accuracy in room layout estimation and emphasize the compatibility between the TPS transformation and panorama images. The robustness of the model in handling both cuboid and non-cuboid room layout estimation is evident with a 3DIoU value of 85.49, 86.16, 81.76, and 91.98 on PanoContext, Stanford-2D3D, Matterport3DLayout, and ZInD datasets, respectively. The source code is available at: https://github.com/HatemHosam/PanoTPS_Net.

---

### Nonlinear discretizations and Newton's method: characterizing stationary points of regression objectives

Authors: Conor Rowan
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11987v1

Second-order methods are emerging as promising alternatives to standard first-order optimizers such as gradient descent and ADAM for training neural networks. Though the advantages of including curvature information in computing optimization steps have been celebrated in the scientific machine learning literature, the only second-order methods that have been studied are quasi-Newton, meaning that the Hessian matrix of the objective function is approximated. Though one would expect only to gain from using the true Hessian in place of its approximation, we show that neural network training reliably fails when relying on exact curvature information. The failure modes provide insight both into the geometry of nonlinear discretizations as well as the distribution of stationary points in the loss landscape, leading us to question the conventional wisdom that the loss landscape is replete with local minima.

---

### Conjecturing: An Overlooked Step in Formal Mathematical Reasoning

Authors: Jasivan Alex Sivakumar, Philipp Borchert, Ronald Cardenas, Gerasimos Lampouras
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11986v1

Autoformalisation, the task of expressing informal mathematical statements in formal language, is often viewed as a direct translation process. This, however, disregards a critical preceding step: conjecturing. Many mathematical problems cannot be formalised directly without first conjecturing a conclusion such as an explicit answer, or a specific bound. Since Large Language Models (LLMs) already struggle with autoformalisation, and the evaluation of their conjecturing ability is limited and often entangled within autoformalisation or proof, it is particularly challenging to understand its effect. To address this gap, we augment existing datasets to create ConjectureBench, and redesign the evaluation framework and metric specifically to measure the conjecturing capabilities of LLMs both as a distinct task and within the autoformalisation pipeline. Our evaluation of foundational models, including GPT-4.1 and DeepSeek-V3.1, reveals that their autoformalisation performance is substantially overestimated when the conjecture is accounted for during evaluation. However, the conjecture should not be assumed to be provided. We design an inference-time method, Lean-FIRe to improve conjecturing and autoformalisation, which, to the best of our knowledge, achieves the first successful end-to-end autoformalisation of 13 PutnamBench problems with GPT-4.1 and 7 with DeepSeek-V3.1. We demonstrate that while LLMs possess the requisite knowledge to generate accurate conjectures, improving autoformalisation performance requires treating conjecturing as an independent task, and investigating further how to correctly integrate it within autoformalisation. Finally, we provide forward-looking guidance to steer future research toward improving conjecturing, an overlooked step of formal mathematical reasoning.

---

### CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research

Authors: Owen Queen, Harrison G. Zhang, James Zou
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11985v1

Variant and gene interpretation are fundamental to personalized medicine and translational biomedicine. However, traditional approaches are manual and labor-intensive. Generative language models (LMs) can facilitate this process, accelerating the translation of fundamental research into clinically-actionable insights. While existing benchmarks have attempted to quantify the capabilities of LMs for interpreting scientific data, these studies focus on narrow tasks that do not translate to real-world research. To meet these challenges, we introduce CGBench, a robust benchmark that tests reasoning capabilities of LMs on scientific publications. CGBench is built from ClinGen, a resource of expert-curated literature interpretations in clinical genetics. CGBench measures the ability to 1) extract relevant experimental results following precise protocols and guidelines, 2) judge the strength of evidence, and 3) categorize and describe the relevant outcome of experiments. We test 8 different LMs and find that while models show promise, substantial gaps exist in literature interpretation, especially on fine-grained instructions. Reasoning models excel in fine-grained tasks but non-reasoning models are better at high-level interpretations. Finally, we measure LM explanations against human explanations with an LM judge approach, revealing that models often hallucinate or misinterpret results even when correctly classifying evidence. CGBench reveals strengths and weaknesses of LMs for precise interpretation of scientific publications, opening avenues for future research in AI for clinical genetics and science more broadly.

---

### Learning by Steering the Neural Dynamics: A Statistical Mechanics Perspective

Authors: Mattia Scardecchia
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11984v1

Despite the striking successes of deep neural networks trained with gradient-based optimization, these methods differ fundamentally from their biological counterparts. This gap raises key questions about how nature achieves robust, sample-efficient learning at minimal energy costs and solves the credit-assignment problem without backpropagation. We take a step toward bridging contemporary AI and computational neuroscience by studying how neural dynamics can support fully local, distributed learning that scales to simple machine-learning benchmarks. Using tools from statistical mechanics, we identify conditions for the emergence of robust dynamical attractors in random asymmetric recurrent networks. We derive a closed-form expression for the number of fixed points as a function of self-coupling strength, and we reveal a phase transition in their structure: below a critical self-coupling, isolated fixed points coexist with exponentially many narrow clusters showing the overlap-gap property; above it, subdominant yet dense and extensive clusters appear. These fixed points become accessible, including to a simple asynchronous dynamical rule, after an algorithm-dependent self-coupling threshold. Building on this analysis, we propose a biologically plausible algorithm for supervised learning with any binary recurrent network. Inputs are mapped to fixed points of the dynamics, by relaxing under transient external stimuli and stabilizing the resulting configurations via local plasticity. We show that our algorithm can learn an entangled version of MNIST, leverages depth to develop hierarchical representations and increase hetero-association capacity, and is applicable to several architectures. Finally, we highlight the strong connection between algorithm performance and the unveiled phase transition, and we suggest a cortex-inspired alternative to self-couplings for its emergence.

---

### Learning Dynamics of VLM Finetuning

Authors: Jusheng Zhang, Kaitong Cai, Jing Yang, Keze Wang
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11978v1

Preference-based finetuning of vision--language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as \textbf{learning-dynamics--aware optimization} and introduce \textbf{Cooling-Weighted DPO (CW-DPO)}, a two-stage recipe that explicitly models and exploits the training trajectory. \textbf{Stage 1} performs supervised finetuning with \textbf{gentle negatives}: \textbf{low-weight smoothed supervision} that regularizes the base policy and curbs overconfidence without explicit penalties. \textbf{Stage 2} applies a DPO objective in which the \textbf{negative term is scaled by a cooling weight} computed from the model's \textbf{average token log-probability} on each negative, suppressing uninformative gradients from easy or off-distribution samples while preserving signal from hard negatives. In practice, we emphasize \textbf{on-policy negatives} and allow \textbf{mixed negatives} by blending a controllable fraction of dataset negatives to maintain contrast freshness. Throughout, we instrument training with $Δ\!\log p$ probes on positives and negatives as first-class signals for early stopping, curriculum design, and failure diagnosis. Across diverse VLM tasks, CW-DPO yields \textbf{more stable optimization}, \textbf{better calibration}, and \textbf{higher pairwise win-rates} than SFT-only and vanilla DPO, while \textbf{converging in fewer steps}. Ablations isolate the \textbf{cooling-weight mechanism} as the primary driver of these gains and show complementary benefits from mixing on-policy and dataset negatives. Taken together, our results show that \textbf{smoothing learning dynamics before cooling preferences} is a simple, general principle for robust VLM alignment.

---

### Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation

Authors: Sayash Kapoor, Benedikt Stroebl, Peter Kirgis, Nitya Nadgir, Zachary S Siegel, Boyi Wei, Tianci Xue, Ziru Chen, Felix Chen, Saiteja Utpala, Franck Ndzomga, Dheeraj Oruganty et al.
Published: 2025-10-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.11977v1

AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic Agent Leaderboard (HAL) to address these challenges. We make three main contributions. First, we provide a standardized evaluation harness that orchestrates parallel evaluations across hundreds of VMs, reducing evaluation time from weeks to hours while eliminating common implementation bugs. Second, we conduct three-dimensional analysis spanning models, scaffolds, and benchmarks. We validate the harness by conducting 21,730 agent rollouts across 9 models and 9 benchmarks in coding, web navigation, science, and customer service with a total cost of about $40,000. Our analysis reveals surprising insights, such as higher reasoning effort reducing accuracy in the majority of runs. Third, we use LLM-aided log inspection to uncover previously unreported behaviors, such as searching for the benchmark on HuggingFace instead of solving a task, or misusing credit cards in flight booking tasks. We share all agent logs, comprising 2.5B tokens of language model calls, to incentivize further research into agent behavior. By standardizing how the field evaluates agents and addressing common pitfalls in agent evaluation, we hope to shift the focus from agents that ace benchmarks to agents that work reliably in the real world.

---

### CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence

Authors: Yutong Cheng, Yang Liu, Changze Li, Dawn Song, Peng Gao
Published: 2025-10-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.11974v2

Cyber Threat Intelligence (CTI) is foundational to modern cybersecurity, enabling organizations to proactively defend against evolving threats. However, the sheer volume and heterogeneity of CTI data, spanning structured knowledge bases (CVE, CWE, CAPEC, MITRE ATT&CK) and unstructured threat reports, far exceed the capacity of manual analysis. The strong contextual understanding and reasoning of Large Language Models (LLMs) have driven growing interest in applying them to CTI tasks. Yet no existing benchmark evaluates LLMs in a retrieval-augmented setting with a proper evaluation harness that grants access to the heterogeneous domain knowledge sources analysts rely on in practice. To address this gap, we present CTIConnect, a benchmark for systematically evaluating retrieval-augmented LLMs across the CTI task landscape. We construct a unified evaluation environment integrating five heterogeneous CTI sources into 1,860 expert-verified QA pairs spanning nine tasks across three categories: Entity Linking, Multi-Document Synthesis, and Entity Attribution. Extensive experiments on ten state-of-the-art LLMs reveal that the cross-source semantic gap manifests differently across task categories, demanding fundamentally different retrieval strategies, and that the performance bottleneck shifts between retrieval infrastructure and evidence utilization depending on the task. Our domain-specific strategies further outperform stronger general-purpose retrieval paradigms (retrieve-then-rerank, IRCoT), showing that closing this gap requires structural interventions rather than generic retrieval improvements. These findings hold across all ten LLMs, remain consistent on the full benchmark, and stay stable under temporal splits spanning 2008-2025. Together, they provide actionable guidance for designing scalable retrieval architectures over heterogeneous CTI ecosystems.

---

### Scaling Long-Horizon LLM Agent via Context-Folding

Authors: Weiwei Sun, Miao Lu, Zhan Ling, Kang Liu, Xuesong Yao, Yiming Yang, Jiecao Chen
Published: 2025-10-13
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.11967v1

Large language model (LLM) agents are fundamentally constrained by context length on long-horizon tasks. We introduce Context-Folding, a framework that empowers agents to actively manage their working context. An agent can procedurally branch into a sub-trajectory to handle a subtask and then fold it upon completion, collapsing the intermediate steps while retaining a concise summary of the outcome. To make this behavior learnable, we develop an end-to-end reinforcement learning framework FoldGRPO with specific process rewards to encourage effective task decomposition and context management. On complex long-horizon tasks (Deep Research and SWE), our folding agent matches or outperforms the ReAct baselines while using an active context 10$\times$ smaller and significantly outperforms models that rely on summarization-based context management.

---

### QLENS: Towards A Quantum Perspective of Language Transformers

Authors: Aditya Gupta, Kirandeep Kaur, Vinayak Gupta, Chirag Shah
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11963v2

In natural language processing, current methods for understanding Transformers are successful at identifying intermediate predictions during a model's inference. However, these approaches function as limited diagnostic checkpoints, lacking a mathematical framework for mechanistically modeling how each layer facilitates transitions between these evolving states. This interpretability gap and past successes of interdisciplinary outlooks inspire us to turn to physics in search of a descriptive mathematical framework for Transformers. We observe that language models are intrinsically probabilistic, an attribute that is echoed in the core postulates of quantum mechanics. This parallel inspires us to translate insights from this discipline to that of natural language processing. Towards this objective, we propose QLENS a novel attempt to develop a physics-based perspective on the Transformer generation process. Under QLENS, a Transformer is studied by converting its latent activations into a state vector in a Hilbert space derived from the model's output units. This state subsequently evolves through hidden layers - reformulated as unitary operators and analogously defined Hamiltonians - during inference. The model's final probability distribution is obtained by applying the Born rule to the end state using a specific measurement operator. To demonstrate QLENS's potential, we conduct a proof-of-concept by probing a toy Transformer to investigate the influence of individual layers in a model's prediction trajectory. We present our work as a foundation for cross-domain insights to be leveraged towards a broader understanding of Transformers.

---

### MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics

Authors: Bowei Guo, Shengkun Tang, Cong Zeng, Zhiqiang Shen
Published: 2025-10-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.11962v1

Diffusion models are renowned for their generative capabilities, yet their pretraining processes exhibit distinct phases of learning speed that have been entirely overlooked in prior post-training acceleration efforts in the community. In this study, we introduce a novel framework called MosaicDiff that aligns diffusion pretraining dynamics with post-training sampling acceleration via trajectory-aware structural pruning. Our approach leverages the observation that the middle, fast-learning stage of diffusion pretraining requires more conservative pruning to preserve critical model features, while the early and later, slow-learning stages benefit from a more aggressive pruning strategy. This adaptive pruning mechanism is the first to explicitly mirror the inherent learning speed variations of diffusion pretraining, thereby harmonizing the model's inner training dynamics with its accelerated sampling process. Extensive experiments on DiT and SDXL demonstrate that our method achieves significant speed-ups in sampling without compromising output quality, outperforming previous state-of-the-art methods by large margins, also providing a new viewpoint for more efficient and robust training-free diffusion acceleration.

---

### Direct Multi-Token Decoding

Authors: Xuan Luo, Weizhi Wang, Xifeng Yan
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11958v1

Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs, early, middle, and late layers may serve distinct roles: Early layers focus on understanding the input context, middle layers handle task-specific processing, and late layers convert abstract representations into output tokens. We hypothesize that once representations have been processed by the early and middle layers, the resulting hidden states may encapsulate sufficient information to support the generation of multiple tokens using only the late layers, eliminating the need to repeatedly traverse the early and middle layers. We refer to this inference paradigm as Direct Multi-Token Decoding (DMTD). Unlike speculative decoding, our method introduces no additional parameters, auxiliary routines, or post-generation verification. Despite being trained on a limited dataset, a fine-tuned DMTD Qwen3-4B model has already demonstrated promising results, achieving up to a 2x speedup with only minor performance loss. Moreover, as shown in our scaling analysis, its performance is expected to further improve with larger training datasets.

---

### Investigating Retrieval-Augmented Generation Systems on Unanswerable, Uncheatable, Realistic, Multi-hop Queries

Authors: Gabrielle Kaili-May Liu, Bryan Li, Arman Cohan, William Gantt Walden, Eugene Yang
Published: 2025-10-13
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.11956v3

Real-world use cases often present RAG systems with complex queries for which relevant information is missing from the corpus or is incomplete. In these settings, RAG systems must be able to reject unanswerable, out-of-scope queries and identify failures of retrieval and multi-hop reasoning. Despite this, existing RAG benchmarks rarely reflect realistic task complexity for multi-hop or out-of-scope questions, which often can be cheated via disconnected reasoning (i.e., solved without genuine multi-hop inference) or require only simple factual recall. This limits the ability for such benchmarks to uncover limitations of existing RAG systems. To address this gap, we present the first pipeline for automatic, difficulty-controlled creation of un$\underline{c}$heatable, $\underline{r}$ealistic, $\underline{u}$nanswerable, and $\underline{m}$ulti-hop $\underline{q}$uerie$\underline{s}$ (CRUMQs), adaptable to any corpus and domain. We use our pipeline to create CRUMQs over two popular RAG datasets and demonstrate its effectiveness via benchmark experiments on leading retrieval-augmented LLMs. Results show that compared to prior RAG benchmarks, CRUMQs are highly challenging for RAG systems and achieve up to 81.0\% reduction in cheatability scores. More broadly, our pipeline offers a simple way to enhance benchmark difficulty and drive development of more capable RAG systems.

---

### Y-Shaped Generative Flows

Authors: Arip Asadulaev, Semyon Semenov, Abduragim Shtanchaev, Eric Moulines, Fakhri Karray, Martin Takac
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11955v3

Modern continuous-time generative models typically induce \emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior to the data. Although effective, this independent movement overlooks the hierarchical structures that exist in real-world data. To address this, we introduce \emph{Y-shaped generative flows}, a framework in which samples travel together along shared pathways before branching off to target-specific endpoints. Our formulation is theoretically justified, yet remains practical, requiring only minimal modifications to standard velocity-driven models. We implement this through a scalable, neural network-based training objective. Experiments on synthetic, image, and biological datasets demonstrate that our method recovers hierarchy-aware structures, improves distributional metrics over strong flow-based baselines, and reaches targets in fewer steps.

---

### Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors

Authors: Quentin Fruytier, Akshay Malhotra, Shahab Hamidi-Rad, Aditya Sant, Aryan Mokhtari, Sujay Sanghavi
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11953v1

Learning disentangled representations, where distinct factors of variation are captured by independent latent variables, is a central goal in machine learning. The dominant approach has been the Variational Autoencoder (VAE) framework, which uses a Kullback-Leibler (KL) divergence penalty to encourage the latent space to match a factorized Gaussian prior. In this work, however, we provide direct evidence that this KL-based regularizer is an unreliable mechanism, consistently failing to enforce the target distribution on the aggregate posterior. We validate this and quantify the resulting entanglement using our novel, unsupervised Latent Predictability Score (LPS). To address this failure, we introduce the Programmable Prior Framework, a method built on the Maximum Mean Discrepancy (MMD). Our framework allows practitioners to explicitly sculpt the latent space, achieving state-of-the-art mutual independence on complex datasets like CIFAR-10 and Tiny ImageNet without the common reconstruction trade-off. Furthermore, we demonstrate how this programmability can be used to engineer sophisticated priors that improve alignment with semantically meaningful features. Ultimately, our work provides a foundational tool for representation engineering, opening new avenues for model identifiability and causal reasoning.

---

### GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences

Authors: Priyanka Dey, Daniele Rosa, Wenqing Zheng, Daniel Barcklow, Jieyu Zhao, Emilio Ferrara
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11952v2

Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. To reduce the reliance on human annotations, we introduce GRAVITY (Generative Response with Aligned Values, Interests, and Traits of You), a framework for generating synthetic, profile-grounded preference data that captures users' interests, values, beliefs, and personality traits. By integrating demographic, cultural, and psychological frameworks -- including Hofstede's cultural dimensions, Schwartz's basic values, the World Values Survey, and Big Five OCEAN traits -- GRAVITY synthesizes preference pairs to guide personalized content generation. We evaluate GRAVITY on book descriptions for 400 Amazon users, comparing it to prompt-based conditioning, standard fine-tuning, and naive synthetic pair generation. Profile-grounded synthetic data consistently improves generation, especially across multiple cultures (USA, Brazil, Japan, India), achieving over 4% higher preference gains across baselines, with user studies showing that GRAVITY outputs are preferred over 86% of the time. Our results show that scenario-grounded synthetic data can capture richer user variation, reduce reliance on costly annotation, and produce more engaging, user-centered content, offering a scalable path for LLM personalization.

---

### TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition

Authors: Yupei Li, Philipp Borchert, Gerasimos Lampouras
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11944v2

Large Language Models (LLMs) excel at both informal and formal (e.g. Lean 4) mathematical reasoning but still struggle with autoformalisation, the task of transforming informal into formal mathematical statements. Yet, the performance of current Math LLMs is constrained by the scarcity of large-scale corpora, particularly those containing pairs of informal and formal statements. Interestingly, the formal languages used in autoformalisation share structural similarities with programming languages, and code data is available at scale. However, current models trained on code do not transfer effectively to formal math, due to structural and syntactic differences between them. To address this, we propose TopoAlign, a framework that unlocks widely available code repositories as training resources for Math LLMs. TopoAlign decomposes code into docstrings, main functions, and dependency functions, and reassembles these components into analogues that structurally mirror formal statements. We train three state-of-the-art models, DeepSeek-Math, Qwen-3 and Herald, and evaluate them on the MiniF2F, Putnam, and ProofNet benchmarks. TopoAlign provides substantial gains for DeepSeek-Math, improving performance by 17.77% on BEq@10 and 68.82% on typecheck@10, and also measurably improves Herald by 0.12% on BEq@10 and 1.09% on typecheck@10 despite introducing no new mathematical knowledge.

---

### On efficiently computable functions, deep networks and sparse compositionality

Authors: Tomaso Poggio
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11942v1

We show that \emph{efficient Turing computability} at any fixed input/output precision implies the existence of \emph{compositionally sparse} (bounded-fan-in, polynomial-size) DAG representations and of corresponding neural approximants achieving the target precision. Concretely: if $f:(0,1)^d\to\R^m$ is computable in time polynomial in the bit-depths, then for every pair of precisions $(n,m_{\mathrm{out}})$ there exists a bounded-fan-in Boolean circuit of size and depth $\poly(n+m_{\mathrm{out}})$ computing the discretized map; replacing each gate by a constant-size neural emulator yields a deep network of size/depth $\poly(n+m_{\mathrm{out}})$ that achieves accuracy $\varepsilon=2^{-m_{\mathrm{out}}}$. We also relate these constructions to compositional approximation rates \cite{MhaskarPoggio2016b,poggio_deep_shallow_2017,Poggio2017,Poggio2023HowDS} and to optimization viewed as hierarchical search over sparse structures.

---

### Efficient Restarts in Non-Stationary Model-Free Reinforcement Learning

Authors: Hiroshi Nonaka, Simon Ambrozak, Sofia R. Miskala-Dinc, Amedeo Ercole, Aviva Prins
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11933v1

In this work, we propose three efficient restart paradigms for model-free non-stationary reinforcement learning (RL). We identify two core issues with the restart design of Mao et al. (2022)'s RestartQ-UCB algorithm: (1) complete forgetting, where all the information learned about an environment is lost after a restart, and (2) scheduled restarts, in which restarts occur only at predefined timings, regardless of the incompatibility of the policy with the current environment dynamics. We introduce three approaches, which we call partial, adaptive, and selective restarts to modify the algorithms RestartQ-UCB and RANDOMIZEDQ (Wang et al., 2025). We find near-optimal empirical performance in multiple different environments, decreasing dynamic regret by up to $91$% relative to RestartQ-UCB.

---

### Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering

Authors: Lorena Calvo-Bartolomé, Valérie Aldana, Karla Cantarero, Alonso Madroñal de Mesa, Jerónimo Arenas-García, Jordan Boyd-Graber
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11928v1

Multilingual question answering (QA) systems must ensure factual consistency across languages, especially for objective queries such as What is jaundice?, while also accounting for cultural variation in subjective responses. We propose MIND, a user-in-the-loop fact-checking pipeline to detect factual and cultural discrepancies in multilingual QA knowledge bases. MIND highlights divergent answers to culturally sensitive questions (e.g., Who assists in childbirth?) that vary by region and context. We evaluate MIND on a bilingual QA system in the maternal and infant health domain and release a dataset of bilingual questions annotated for factual and cultural inconsistencies. We further test MIND on datasets from other domains to assess generalization. In all cases, MIND reliably identifies inconsistencies, supporting the development of more culturally aware and factually consistent QA systems.

---

### Indoor Localization using Compact, Telemetry-Agnostic, Transfer-Learning Enabled Decoder-Only Transformer

Authors: Nayan Sanjay Bhatia, Pranay Kocheta, Russell Elliott, Harikrishna S. Kuttivelil, Katia Obraczka
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11926v1

Indoor Wi-Fi positioning remains a challenging problem due to the high sensitivity of radio signals to environmental dynamics, channel propagation characteristics, and hardware heterogeneity. Conventional fingerprinting and model-based approaches typically require labor-intensive calibration and suffer rapid performance degradation when devices, channel or deployment conditions change. In this paper, we introduce Locaris, a decoder-only large language model (LLM) for indoor localization. Locaris treats each access point (AP) measurement as a token, enabling the ingestion of raw Wi-Fi telemetry without pre-processing. By fine-tuning its LLM on different Wi-Fi datasets, Locaris learns a lightweight and generalizable mapping from raw signals directly to device location. Our experimental study comparing Locaris with state-of-the-art methods consistently shows that Locaris matches or surpasses existing techniques for various types of telemetry. Our results demonstrate that compact LLMs can serve as calibration-free regression models for indoor localization, offering scalable and robust cross-environment performance in heterogeneous Wi-Fi deployments. Few-shot adaptation experiments, using only a handful of calibration points per device, further show that Locaris maintains high accuracy when applied to previously unseen devices and deployment scenarios. This yields sub-meter accuracy with just a few hundred samples, robust performance under missing APs and supports any and all available telemetry. Our findings highlight the practical viability of Locaris for indoor positioning in the real-world scenarios, particularly in large-scale deployments where extensive calibration is infeasible.

---

### Inpainting the Neural Picture: Inferring Unrecorded Brain Area Dynamics from Multi-Animal Datasets

Authors: Ji Xia, Yizi Zhang, Shuqi Wang, Genevera I. Allen, Liam Paninski, Cole Lincoln Hurwitz, Kenneth D. Miller
Published: 2025-10-13
Categories: q-bio.NC, stat.AP, stat.ML
arXiv: https://arxiv.org/abs/2510.11924v1

Characterizing interactions between brain areas is a fundamental goal of systems neuroscience. While such analyses are possible when areas are recorded simultaneously, it is rare to observe all combinations of areas of interest within a single animal or recording session. How can we leverage multi-animal datasets to better understand multi-area interactions? Building on recent progress in large-scale, multi-animal models, we introduce NeuroPaint, a masked autoencoding approach for inferring the dynamics of unrecorded brain areas. By training across animals with overlapping subsets of recorded areas, NeuroPaint learns to reconstruct activity in missing areas based on shared structure across individuals. We train and evaluate our approach on synthetic data and two multi-animal, multi-area Neuropixels datasets. Our results demonstrate that models trained across animals with partial observations can successfully in-paint the dynamics of unrecorded areas, enabling multi-area analyses that transcend the limitations of any single experiment.

---

### Enhancing Diffusion-Based Sampling with Molecular Collective Variables

Authors: Juno Nam, Bálint Máté, Artur P. Toshev, Manasa Kaniselvan, Rafael Gómez-Bombarelli, Ricky T. Q. Chen, Brandon Wood, Guan-Horng Liu, Benjamin Kurt Miller
Published: 2025-10-13
Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.11923v2

Diffusion-based samplers learn to sample complex, high-dimensional distributions using energies or log densities alone, without training data. Yet, they remain impractical for molecular sampling because they are often slower than molecular dynamics and miss thermodynamically relevant modes. Inspired by enhanced sampling, we encourage exploration by introducing a sequential bias along bespoke, information-rich, low-dimensional projections of atomic coordinates known as collective variables (CVs). We introduce a repulsive potential centered on the CVs from recent samples, which pushes future samples towards novel CV regions and effectively increases the temperature in the projected space. Our resulting method improves efficiency, mode discovery, enables the estimation of free energy differences, and retains independent sampling from the approximate Boltzmann distribution via reweighting by the bias. On standard peptide conformational sampling benchmarks, the method recovers diverse conformational states and accurate free energy profiles. We are the first to demonstrate reactive sampling using a diffusion-based sampler, capturing bond breaking and formation with universal interatomic potentials at near-first-principles accuracy. The approach resolves reactive energy landscapes at a fraction of the wall-clock time of standard sampling methods, advancing diffusion-based sampling towards practical use in molecular sciences.

---

### LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens

Authors: Armel Zebaze, Rachel Bawden, Benoît Sagot
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11919v1

Large reasoning models (LRMs) have led to new possibilities in terms of problem-solving, through the devising of a natural language thought process prior to answering a query. While their capabilities are well known across mathematics and coding tasks, their impact on the task of machine translation (MT) remains underexplored. In this work, we explore the benefits of the generation of intermediate tokens when performing MT across multiple language pairs of different levels of resourcedness and multiple setups. We find that "thinking tokens" do not help LRMs better perform MT. This result generalizes to models fine-tuned to reason before translating using distilled chain of thought (CoT) inspired by human translators' practices. Specifically, fine-tuning a model with synthetic CoT explanations detailing how to translate step-by-step does not outperform standard input-output fine-tuning. However, constructing the intermediate tokens by combining the outputs of modular translation-specific prompting strategies results in improvements. Our findings underscore that the contribution of intermediate tokens during fine-tuning highly depends on the presence of translation attempts within them. More broadly, our results suggest that using a teacher to refine target translations or to expand parallel corpora is more impactful than distilling their CoT explanations into "thinking" MT models.

---

### Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networks

Authors: Jun-En Ding, Anna Zilverstand, Shihao Yang, Albert Chih-Chieh Yang, Feng Liu
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11917v4

Dementia disorders such as Alzheimer's disease (AD) and frontotemporal dementia (FTD) exhibit overlapping electrophysiological signatures in electroencephalography (EEG) that challenge accurate diagnosis. Existing EEG-based methods are limited by full-band frequency analysis, which hinders precise differentiation of dementia subtypes and severity stages. To address this limitation, we propose a Variational Mixture of Graph Neural Experts (VMoGE) framework that integrates multi-band EEG analysis with variational graph neural networks and a mixture-of-experts architecture. Each expert specializes in a specific EEG frequency band and models brain connectivity using a Gaussian Markov Random Field prior, while a variational gating mechanism adaptively integrates expert outputs. This design enables the model to learn frequency-specific brain network representations while modeling latent uncertainty through variational inference. Experimental results on two EEG dementia datasets show that VMoGE achieves strong performance, with an area under the curve (AUC) of 0.89 for healthy controls (HC) vs. AD classification in the main comparison and competitive results across dementia subtyping and Clinical Dementia Rating (CDR) staging tasks. Clinically, VMoGE offers three key translational values: the expert gating weights correlate with Mini-Mental State Examination (MMSE) scores and CDR severity, slow-wave $δ/ θ$-band contributions are associated with AD-related EEG slowing and disease progression, and spatially localized activation maps reveal posterior $θ$/$α$-band alterations and region-specific $β$-band changes, providing neurophysiologically interpretable patterns aligned with known AD neuropathology.

---

### Simplifying Optimal Transport through Schatten-$p$ Regularization

Authors: Tyler Maunu
Published: 2025-10-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.11910v1

We propose a new general framework for recovering low-rank structure in optimal transport using Schatten-$p$ norm regularization. Our approach extends existing methods that promote sparse and interpretable transport maps or plans, while providing a unified and principled family of convex programs that encourage low-dimensional structure. The convexity of our formulation enables direct theoretical analysis: we derive optimality conditions and prove recovery guarantees for low-rank couplings and barycentric maps in simplified settings. To efficiently solve the proposed program, we develop a mirror descent algorithm with convergence guarantees for $p \geq 1$. Experiments on synthetic and real data demonstrate the method's efficiency, scalability, and ability to recover low-rank transport structures.

---

### Task-Specific Dual-Model Framework for Comprehensive Traffic Safety Video Description and Analysis

Authors: Blessing Agyei Kyem, Neema Jakisa Owor, Andrews Danyo, Joshua Kofi Asamoah, Eugene Denteh, Tanner Muturi, Anthony Dontoh, Yaw Adu-Gyamfi, Armstrong Aboah
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11907v1

Traffic safety analysis requires complex video understanding to capture fine-grained behavioral patterns and generate comprehensive descriptions for accident prevention. In this work, we present a unique dual-model framework that strategically utilizes the complementary strengths of VideoLLaMA and Qwen2.5-VL through task-specific optimization to address this issue. The core insight behind our approach is that separating training for captioning and visual question answering (VQA) tasks minimizes task interference and allows each model to specialize more effectively. Experimental results demonstrate that VideoLLaMA is particularly effective in temporal reasoning, achieving a CIDEr score of 1.1001, while Qwen2.5-VL excels in visual understanding with a VQA accuracy of 60.80\%. Through extensive experiments on the WTS dataset, our method achieves an S2 score of 45.7572 in the 2025 AI City Challenge Track 2, placing 10th on the challenge leaderboard. Ablation studies validate that our separate training strategy outperforms joint training by 8.6\% in VQA accuracy while maintaining captioning quality.

---

### LLM Knowledge is Brittle: Truthfulness Representations Rely on Superficial Resemblance

Authors: Patrick Haller, Mark Ibrahim, Polina Kirichenko, Levent Sagun, Samuel J. Bell
Published: 2025-10-13
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.11905v1

For Large Language Models (LLMs) to be reliable, they must learn robust knowledge that can be generally applied in diverse settings -- often unlike those seen during training. Yet, extensive research has shown that LLM performance can be brittle, with models exhibiting excessive sensitivity to trivial input variations. In this work, we explore whether this brittleness is a direct result of unstable internal knowledge representations. To explore this question, we build on previous work showing that LLM representations encode statement truthfulness -- i.e., true, factual statements can be easily separated from false, inaccurate ones. Specifically, we test the robustness of learned knowledge by evaluating representation separability on samples that have undergone superficial transformations to drive them out-of-distribution (OOD), such as typos or reformulations. By applying semantically-preserving perturbations, we study how separability degrades as statements become more OOD, across four LLM families, five evaluation datasets, and three knowledge probing methods. Our results reveal that internal representations of statement truthfulness collapse as the samples' presentations become less similar to those seen during pre-training. While LLMs can often distinguish between true and false statements when they closely resemble the pre-training data, this ability is highly dependent on the statement's exact surface form. These findings offer a possible explanation for brittle benchmark performance: LLMs may learn shallow, non-robust knowledge representations that allow for only limited generalizability. Our work presents a fundamental challenge for the utility of truthfulness probes, and more broadly, calls for further research on improving the robustness of learned knowledge representations.

---

### Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks

Authors: Rizal Fathony, Igor Melnyk, Owen Reinert, Nam H. Nguyen, Daniele Rosa, C. Bayan Bruss
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11903v2

User event modeling plays a central role in many machine learning applications, with use cases spanning e-commerce, social media, finance, cybersecurity, and other domains. User events can be broadly categorized into personal events, which involve individual actions, and relational events, which involve interactions between two users. These two types of events are typically modeled separately, using sequence-based methods for personal events and graph-based methods for relational events. Despite the need to capture both event types in real-world systems, prior work has rarely considered them together. This is often due to the convenient simplification that user behavior can be adequately represented by a single formalization, either as a sequence or a graph. To address this gap, there is a need for public datasets and prediction tasks that explicitly incorporate both personal and relational events. In this work, we introduce a collection of such datasets, propose a unified formalization, and empirically show that models benefit from incorporating both event types. Our results also indicate that current methods leave a notable room for improvements. We release these resources to support further research in unified user event modeling and encourage progress in this direction.

---

### ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertainty

Authors: Chenliang Li, Junyu Leng, Jiaxiang Li, Youbang Sun, Shixiang Chen, Shahin Shahrampour, Alfredo Garcia
Published: 2025-10-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.11899v1

Robust reinforcement learning (Robust RL) seeks to handle epistemic uncertainty in environment dynamics, but existing approaches often rely on nested min--max optimization, which is computationally expensive and yields overly conservative policies. We propose \textbf{Adaptive Rank Representation (AdaRL)}, a bi-level optimization framework that improves robustness by aligning policy complexity with the intrinsic dimension of the task. At the lower level, AdaRL performs policy optimization under fixed-rank constraints with dynamics sampled from a Wasserstein ball around a centroid model. At the upper level, it adaptively adjusts the rank to balance the bias--variance trade-off, projecting policy parameters onto a low-rank manifold. This design avoids solving adversarial worst-case dynamics while ensuring robustness without over-parameterization. Empirical results on MuJoCo continuous control benchmarks demonstrate that AdaRL not only consistently outperforms fixed-rank baselines (e.g., SAC) and state-of-the-art robust RL methods (e.g., RNAC, Parseval), but also converges toward the intrinsic rank of the underlying tasks. These results highlight that adaptive low-rank policy representations provide an efficient and principled alternative for robust RL under model uncertainty.

---

### High-Probability Bounds For Heterogeneous Local Differential Privacy

Authors: Maryam Aliakbarpour, Alireza Fallah, Swaha Roy, Ria Stevens
Published: 2025-10-13
Categories: stat.ML, cs.CR, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2510.11895v1

We study statistical estimation under local differential privacy (LDP) when users may hold heterogeneous privacy levels and accuracy must be guaranteed with high probability. Departing from the common in-expectation analyses, and for one-dimensional and multi-dimensional mean estimation problems, we develop finite sample upper bounds in $\ell_2$-norm that hold with probability at least $1-β$. We complement these results with matching minimax lower bounds, establishing the optimality (up to constants) of our guarantees in the heterogeneous LDP regime. We further study distribution learning in $\ell_\infty$-distance, designing an algorithm with high-probability guarantees under heterogeneous privacy demands. Our techniques offer principled guidance for designing mechanisms in settings with user-specific privacy levels.

---

### R-WoM: Retrieval-augmented World Model For Computer-use Agents

Authors: Kai Mei, Jiang Guo, Shuaichen Chang, Mingwen Dong, Dongkyu Lee, Xing Niu, Jiarong Jiang
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11892v2

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However, this capability is fundamentally limited by LLMs' tendency toward hallucination and their reliance on static training knowledge, which can lead to compounding errors that inhibit long-horizon simulations. To systematically investigate whether LLMs are appropriate for world modeling, we probe two core capabilities of world models--future state prediction and reward estimation--through three tasks: next-state identification, full-procedure planning alignment, and milestone transition recognition. Our analysis shows that while LLMs effectively capture immediate next states and identify meaningful state transitions, their performance rapidly degrades in full-procedure planning. This highlights LLMs' limitations in reliably modeling environment dynamics over long horizons. To address these limitations, we propose the Retrieval-augmented World Model (R-WoM), which grounds LLM simulations by incorporating factual, up-to-date knowledge retrieved from external tutorials. Experiments show that R-WoM achieves relative improvements of up to 23.4% and 16.3% on the subsets of OSWorld and Webarena compared to baselines, with particular advantage in longer-horizon simulations.

---

### MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images

Authors: Sicheng Zhou, Lei Wu, Cao Xiao, Parminder Bhatia, Taha Kass-Hout
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11883v1

Self-supervised learning (SSL) has transformed vision encoder training in general domains but remains underutilized in medical imaging due to limited data and domain specific biases. We present MammoDINO, a novel SSL framework for mammography, pretrained on 1.4 million mammographic images. To capture clinically meaningful features, we introduce a breast tissue aware data augmentation sampler for both image-level and patch-level supervision and a cross-slice contrastive learning objective that leverages 3D digital breast tomosynthesis (DBT) structure into 2D pretraining. MammoDINO achieves state-of-the-art performance on multiple breast cancer screening tasks and generalizes well across five benchmark datasets. It offers a scalable, annotation-free foundation for multipurpose computer-aided diagnosis (CAD) tools for mammogram, helping reduce radiologists' workload and improve diagnostic efficiency in breast cancer screening.

---

### GS-Verse: Mesh-based Gaussian Splatting for Physics-aware Interaction in Virtual Reality

Authors: Anastasiya Pechko, Piotr Borycki, Joanna Waczyńska, Daniel Barczyk, Agata Szymańska, Sławomir Tadeja, Przemysław Spurek
Published: 2025-10-13
Categories: cs.GR, cs.CV
arXiv: https://arxiv.org/abs/2510.11878v2

As the demand for immersive 3D content grows, the need for intuitive and efficient interaction methods becomes paramount. Current techniques for physically manipulating 3D content within Virtual Reality (VR) often face significant limitations, including reliance on engineering-intensive processes and simplified geometric representations, such as tetrahedral cages, which can compromise visual fidelity and physical accuracy. In this paper, we introduce GS-Verse (Gaussian Splatting for Virtual Environment Rendering and Scene Editing), a novel method designed to overcome these challenges by directly integrating an object's mesh with a Gaussian Splatting (GS) representation. Our approach enables more precise surface approximation, leading to highly realistic deformations and interactions. By leveraging existing 3D mesh assets, GS-Verse facilitates seamless content reuse and simplifies the development workflow. Moreover, our system is designed to be physics-engine-agnostic, granting developers robust deployment flexibility. This versatile architecture delivers a highly realistic, adaptable, and intuitive approach to interactive 3D manipulation. We rigorously validate our method against the current state-of-the-art technique that couples VR with GS in a comparative user study involving 18 participants. Specifically, we demonstrate that our approach is statistically significantly better for physics-aware stretching manipulation and is also more consistent in other physics-based manipulations like twisting and shaking. Further evaluation across various interactions and scenes confirms that our method consistently delivers high and reliable performance, showing its potential as a plausible alternative to existing methods.

---

### Robust Adversarial Reinforcement Learning in Stochastic Games via Sequence Modeling

Authors: Xiaohang Tang, Zhuowen Cheng, Satyabrat Kumar
Published: 2025-10-13
Categories: cs.LG, cs.GT
arXiv: https://arxiv.org/abs/2510.11877v1

The Transformer, a highly expressive architecture for sequence modeling, has recently been adapted to solve sequential decision-making, most notably through the Decision Transformer (DT), which learns policies by conditioning on desired returns. Yet, the adversarial robustness of reinforcement learning methods based on sequence modeling remains largely unexplored. Here we introduce the Conservative Adversarially Robust Decision Transformer (CART), to our knowledge the first framework designed to enhance the robustness of DT in adversarial stochastic games. We formulate the interaction between the protagonist and the adversary at each stage as a stage game, where the payoff is defined as the expected maximum value over subsequent states, thereby explicitly incorporating stochastic state transitions. By conditioning Transformer policies on the NashQ value derived from these stage games, CART generates policy that are simultaneously less exploitable (adversarially robust) and conservative to transition uncertainty. Empirically, CART achieves more accurate minimax value estimation and consistently attains superior worst-case returns across a range of adversarial stochastic games.

---

### Active Subspaces in Infinite Dimension

Authors: Poorbita Kundu, Nathan Wycoff
Published: 2025-10-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.11871v1

Active subspace analysis uses the leading eigenspace of the gradient's second moment to conduct supervised dimension reduction. In this article, we extend this methodology to real-valued functionals on Hilbert space. We define an operator which coincides with the active subspace matrix when applied to a Euclidean space. We show that many of the desirable properties of Active Subspace analysis extend directly to the infinite dimensional setting. We also propose a Monte Carlo procedure and discuss its convergence properties. Finally, we deploy this methodology to create visualizations and improve modeling and optimization on complex test problems.

---

### Improving Knowledge Graph Embeddings through Contrastive Learning with Negative Statements

Authors: Rita T. Sousa, Heiko Paulheim
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11868v1

Knowledge graphs represent information as structured triples and serve as the backbone for a wide range of applications, including question answering, link prediction, and recommendation systems. A prominent line of research for exploring knowledge graphs involves graph embedding methods, where entities and relations are represented in low-dimensional vector spaces that capture underlying semantics and structure. However, most existing methods rely on assumptions such as the Closed World Assumption or Local Closed World Assumption, treating missing triples as false. This contrasts with the Open World Assumption underlying many real-world knowledge graphs. Furthermore, while explicitly stated negative statements can help distinguish between false and unknown triples, they are rarely included in knowledge graphs and are often overlooked during embedding training. In this work, we introduce a novel approach that integrates explicitly declared negative statements into the knowledge embedding learning process. Our approach employs a dual-model architecture, where two embedding models are trained in parallel, one on positive statements and the other on negative statements. During training, each model generates negative samples by corrupting positive samples and selecting the most likely candidates as scored by the other model. The proposed approach is evaluated on both general-purpose and domain-specific knowledge graphs, with a focus on link prediction and triple classification tasks. The extensive experiments demonstrate that our approach improves predictive performance over state-of-the-art embedding models, demonstrating the value of integrating meaningful negative knowledge into embedding learning.

---

### Actor-Enriched Time Series Forecasting of Process Performance

Authors: Aurelie Leribaux, Rafael Oyamada, Johannes De Smedt, Zahra Dasht Bozorgi, Artem Polyvyanyy, Jochen De Weerdt
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11856v1

Predictive Process Monitoring (PPM) is a key task in Process Mining that aims to predict future behavior, outcomes, or performance indicators. Accurate prediction of the latter is critical for proactive decision-making. Given that processes are often resource-driven, understanding and incorporating actor behavior in forecasting is crucial. Although existing research has incorporated aspects of actor behavior, its role as a time-varying signal in PPM remains limited. This study investigates whether incorporating actor behavior information, modeled as time series, can improve the predictive performance of throughput time (TT) forecasting models. Using real-life event logs, we construct multivariate time series that include TT alongside actor-centric features, i.e., actor involvement, the frequency of continuation, interruption, and handover behaviors, and the duration of these behaviors. We train and compare several models to study the benefits of adding actor behavior. The results show that actor-enriched models consistently outperform baseline models, which only include TT features, in terms of RMSE, MAE, and R2. These findings demonstrate that modeling actor behavior over time and incorporating this information into forecasting models enhances performance indicator predictions.

---

### Evaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detection

Authors: Saroj Basnet, Shafkat Farabi, Tharindu Ranasinghe, Diptesh Kanoji, Marcos Zampieri
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11852v1

Recent advances in open-source vision-language models (VLMs) offer new opportunities for understanding complex and subjective multimodal phenomena such as sarcasm. In this work, we evaluate seven state-of-the-art VLMs - BLIP2, InstructBLIP, OpenFlamingo, LLaVA, PaliGemma, Gemma3, and Qwen-VL - on their ability to detect multimodal sarcasm using zero-, one-, and few-shot prompting. Furthermore, we evaluate the models' capabilities in generating explanations to sarcastic instances. We evaluate the capabilities of VLMs on three benchmark sarcasm datasets (Muse, MMSD2.0, and SarcNet). Our primary objectives are twofold: (1) to quantify each model's performance in detecting sarcastic image-caption pairs, and (2) to assess their ability to generate human-quality explanations that highlight the visual-textual incongruities driving sarcasm. Our results indicate that, while current models achieve moderate success in binary sarcasm detection, they are still not able to generate high-quality explanations without task-specific finetuning.

---

### Deep Research Agents Brings Deeper Harm

Authors: Shuo Chen, Zonggen Li, Xingyu Jin, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu
Published: 2025-10-13
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.11851v3

We reveal that Deep Research (DR) agents systematically expose safety risks: simply submitting harmful queries that a standalone LLM would reject outright can elicit detailed and dangerous reports from DR agents. Empirical analysis reveals that the advantages that make DR agents powerful unintentionally make them vulnerable: both the research role assignment (e.g., Planner) and the multi-step execution mechanism weaken alignment of the base LLM, leading to severe safety breaches. Through linear probe analysis of internal hidden states, we demonstrate that role assignment suppresses refusal awareness by shifting representations away from safety boundaries. Besides, multi-step execution distributes harmfulness across individual steps, preventing alignment mechanisms from being activated throughout the research process. Exploiting these vulnerabilities, we design Intent Hijack (i.e., rephrasing harmful queries as academic research) and Plan Injection (i.e., manipulating execution plans) to further examine the safety risks of DR agents. Extensive experiments show that our methods achieve near-perfect compliance and elicit detailed, actionable reports that significantly exceed standalone LLM outputs in technical depth and applicability. These results demonstrate alarming misalignment in DR agents and underscore the urgent need for tailored alignment techniques. Our code is available in https://schen.app/deeper-harm.

---

### Contrastive Dimension Reduction: A Systematic Review

Authors: Sam Hawke, Eric Zhang, Jiawen Chen, Didong Li
Published: 2025-10-13
Categories: stat.ME, math.ST, stat.CO, stat.ML
arXiv: https://arxiv.org/abs/2510.11847v1

Contrastive dimension reduction (CDR) methods aim to extract signal unique to or enriched in a treatment (foreground) group relative to a control (background) group. This setting arises in many scientific domains, such as genomics, imaging, and time series analysis, where traditional dimension reduction techniques such as Principal Component Analysis (PCA) may fail to isolate the signal of interest. In this review, we provide a systematic overview of existing CDR methods. We propose a pipeline for analyzing case-control studies together with a taxonomy of CDR methods based on their assumptions, objectives, and mathematical formulations, unifying disparate approaches under a shared conceptual framework. We highlight key applications and challenges in existing CDR methods, and identify open questions and future directions. By providing a clear framework for CDR and its applications, we aim to facilitate broader adoption and motivate further developments in this emerging field.

---

### Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities

Authors: Urs Spiegelhalter, Jörg K. H. Franke, Frank Hutter
Published: 2025-10-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.11842v1

Adapting language models to new tasks through continued pretraining faces a fundamental trade-off: models must learn new capabilities while avoiding catastrophic forgetting of existing knowledge. While prior work has studied synthetic data generation techniques, the optimal replay ratios for balancing task performance and knowledge retention under computational constraints remain poorly understood. We present a comprehensive empirical study investigating the interplay between replay ratio configuration and computational budget when adapting language models to new tasks. Using the bAbI reasoning tasks as our target objective, we apply synthetic data generation and systematically evaluate different total token budgets and replay ratio configurations. We analyze their effects on both task mastery and general knowledge retention. Our experiments reveal an optimal configuration that balances task-specific performance with general knowledge retention. Based on our findings, we provide empirically-grounded guidelines for selecting replay ratios based on computational budget, enabling practitioners to achieve strong task adaptation with significantly reduced training costs.

---

### WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation

Authors: Yu-Hsiang Wang, Olgica Milenkovic
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11839v3

Time series are ubiquitous in many applications that involve forecasting, classification and causal inference tasks, such as healthcare, finance, audio signal processing and climate sciences. Still, large, high-quality time series datasets remain scarce. Synthetic generation can address this limitation; however, current models confined either to the time or frequency domains struggle to reproduce the inherently multi-scaled structure of real-world time series. We introduce WaveletDiff, a new framework that trains diffusion models directly on wavelet coefficients to exploit the inherent multi-resolution structure of time series data. The model combines dedicated transformers for each decomposition level with cross-level attention mechanisms that enable selective information exchange between temporal and frequency scales through adaptive gating. It is also informed by level-specific energy constraints based on Parseval's theorem which preserve time-frequency properties throughout the diffusion process. Comprehensive tests across six real-world datasets from energy, finance, and neuroscience domains demonstrate that WaveletDiff outperforms the diffusion baselines FourierDiffusion, Diffusion-TS, and SigDiffusions on the majority of metrics, with the smallest margin over FourierDiffusion, while still achieving roughly 3x lower discriminative and Context-FID scores. Against the VAE/transformer-based MSDformer, the results are mostly comparable, with WaveletDiff using fewer parameters and less training time on most datasets. The most revealing finding is the significant performance gap on fMRI data (in favor of MSDformer) and EEG (in favor of WaveletDiff). This finding is explained via a careful testing/examination of the properties of wavelet coefficients for generative, as opposed to analyses/decomposition tasks. Our code is available at https://github.com/GarlicWang/WaveletDiff.

---

### Countermind: A Multi-Layered Security Architecture for Large Language Models

Authors: Dominik Schwarz
Published: 2025-10-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.11837v1

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which rely on post hoc output filtering, are often brittle and fail to address the root cause: the model's inability to distinguish trusted instructions from untrusted data. This paper proposes Countermind, a multi-layered security architecture intended to shift defenses from a reactive, post hoc posture to a proactive, pre-inference, and intra-inference enforcement model. The architecture proposes a fortified perimeter designed to structurally validate and transform all inputs, and an internal governance mechanism intended to constrain the model's semantic processing pathways before an output is generated. The primary contributions of this work are conceptual designs for: (1) A Semantic Boundary Logic (SBL) with a mandatory, time-coupled Text Crypter intended to reduce the plaintext prompt injection attack surface, provided all ingestion paths are enforced. (2) A Parameter-Space Restriction (PSR) mechanism, leveraging principles from representation engineering, to dynamically control the LLM's access to internal semantic clusters, with the goal of mitigating semantic drift and dangerous emergent behaviors. (3) A Secure, Self-Regulating Core that uses an OODA loop and a learning security module to adapt its defenses based on an immutable audit log. (4) A Multimodal Input Sandbox and Context-Defense mechanisms to address threats from non-textual data and long-term semantic poisoning. This paper outlines an evaluation plan designed to quantify the proposed architecture's effectiveness in reducing the Attack Success Rate (ASR) for form-first attacks and to measure its potential latency overhead.

---

### Data or Language Supervision: What Makes CLIP Better than DINO?

Authors: Yiming Liu, Yuhui Zhang, Dhruba Ghosh, Ludwig Schmidt, Serena Yeung-Levy
Published: 2025-10-13
Categories: cs.CV, cs.AI, cs.CL, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2510.11835v1

CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language supervision or its much larger training data. To disentangle these factors, we pre-train CLIP and DINO under controlled settings -- using the same architecture, dataset, and training configuration -- achieving similar ImageNet accuracy. Embedding analysis shows that CLIP captures high-level semantics (e.g., object categories, text), while DINO is more responsive to low-level features like colors and styles. When integrated into VLMs and evaluated on 20 VQA benchmarks, CLIP excels at text-intensive tasks, while DINO slightly outperforms on vision-centric ones. Variants of language supervision (e.g., sigmoid loss, pre-trained language encoders) yield limited gains. Our findings provide scientific insights into vision encoder design and its impact on VLM performance.

---

### Don't Walk the Line: Boundary Guidance for Filtered Generation

Authors: Sarah Ball, Andreas Haupt
Published: 2025-10-13
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2510.11834v3

Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tune the generator to reduce the probability of being filtered, but this can be suboptimal: it often pushes the model toward producing samples near the classifier's decision boundary, increasing both false positives and false negatives. We propose Boundary Guidance, a reinforcement learning fine-tuning method that explicitly steers generation away from the classifier's margin. On a benchmark of jailbreak, ambiguous, and longcontext prompts, Boundary Guidance improves both the safety and the utility of outputs, as judged by LLM-as-a-Judge evaluations. Comprehensive ablations across model scales and reward designs demonstrate the robustness of our approach.

---

### Z0-Inf: Zeroth Order Approximation for Data Influence

Authors: Narine Kokhlikyan, Kamalika Chaudhuri, Saeed Mahloujifar
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11832v1

A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimating this influence enables critical applications, including data selection and model debugging; in particular, self-influence, which quantifies the influence of a training point on itself, has found many uses in data quality assessment and outlier detection. Existing methods for measuring data influence, however, are often impractical for large models due to low accuracy or prohibitive computational costs: most approaches either provide poor approximations or rely on gradients and inverse-Hessian computations that remain challenging to scale. In this work, we introduce a highly efficient zeroth-order approximation for estimating the influence of training data that requires only a fraction of the time and memory footprint of prior methods. Notably, our method relies solely on loss values of intermediate checkpoints on the training and test data, along with the checkpoints themselves, making it broadly applicable even when the loss function of interest is non-differentiable. Beyond its computational efficiency, our approach achieves superior accuracy in estimating self-influence and comparable or improved accuracy in estimating train-test influence for fine-tuned large language models, enabling scalable and practical analysis of how training data shapes model behavior.

---

### Schrödinger bridge for generative AI: Soft-constrained formulation and convergence analysis

Authors: Jin Ma, Ying Tan, Renyuan Xu
Published: 2025-10-13
Categories: cs.LG, math.DS, math.OC, q-fin.MF
arXiv: https://arxiv.org/abs/2510.11829v2

Generative AI can be framed as the problem of learning a model that maps simple reference measures into complex data distributions, and it has recently found a strong connection to the classical theory of the Schrödinger bridge problems (SBPs) due partly to their common nature of interpolating between prescribed marginals via entropy-regularized stochastic dynamics. However, the classical SBP enforces hard terminal constraints, which often leads to instability in practical implementations, especially in high-dimensional or data-scarce regimes. To address this challenge, we follow the idea of the so-called soft-constrained Schrödinger bridge problem (SCSBP), in which the terminal constraint is replaced by a general penalty function. This relaxation leads to a more flexible stochastic control formulation of McKean-Vlasov type. We establish the existence of optimal solutions for all penalty levels and prove that, as the penalty grows, both the controls and value functions converge to those of the classical SBP at a linear rate. Our analysis builds on Doob's h-transform representations, the stability results of Schrödinger potentials, Gamma-convergence, and a novel fixed-point argument that couples an optimization problem over the space of measures with an auxiliary entropic optimal transport problem. These results not only provide the first quantitative convergence guarantees for soft-constrained bridges but also shed light on how penalty regularization enables robust generative modeling, fine-tuning, and transfer learning.

---

### Combining Euclidean and Hyperbolic Representations for Node-level Anomaly Detection

Authors: Simone Mungari, Ettore Ritacco, Pietro Sabatino
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11827v1

Node-level anomaly detection (NAD) is challenging due to diverse structural patterns and feature distributions. As such, NAD is a critical task with several applications which range from fraud detection, cybersecurity, to recommendation systems. We introduce Janus, a framework that jointly leverages Euclidean and Hyperbolic Graph Neural Networks to capture complementary aspects of node representations. Each node is described by two views, composed by the original features and structural features derived from random walks and degrees, then embedded into Euclidean and Hyperbolic spaces. A multi Graph-Autoencoder framework, equipped with a contrastive learning objective as regularization term, aligns the embeddings across the Euclidean and Hyperbolic spaces, highlighting nodes whose views are difficult to reconcile and are thus likely anomalous. Experiments on four real-world datasets show that Janus consistently outperforms shallow and deep baselines, empirically demonstrating that combining multiple geometric representations provides a robust and effective approach for identifying subtle and complex anomalies in graphs.

---

### Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

Authors: Simin Li, Zihao Mao, Hanxiao Li, Zonglei Jing, Zhuohang bian, Jun Guo, Li Wang, Zhuoran Han, Ruixiao Xu, Xin Yu, Chengdong Ma, Yuqing Ma et al.
Published: 2025-10-13
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.11824v2

In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain robustness and resilience under real-world uncertainties. Building trustworthy MARL systems requires a deep understanding of robustness, which ensures stability under uncertainties, and resilience, the ability to recover from disruptions--a concept extensively studied in control systems but largely overlooked in MARL. In this paper, we present a large-scale empirical study comprising over 82,620 experiments to evaluate cooperation, robustness, and resilience in MARL across 4 real-world environments, 13 uncertainty types, and 15 hyperparameters. Our key findings are: (1) Under mild uncertainty, optimizing cooperation improves robustness and resilience, but this link weakens as perturbations intensify. Robustness and resilience also varies by algorithm and uncertainty type. (2) Robustness and resilience do not generalize across uncertainty modalities or agent scopes: policies robust to action noise for all agents may fail under observation noise on a single agent. (3) Hyperparameter tuning is critical for trustworthy MARL: surprisingly, standard practices like parameter sharing, GAE, and PopArt can hurt robustness, while early stopping, high critic learning rates, and Leaky ReLU consistently help. By optimizing hyperparameters only, we observe substantial improvement in cooperation, robustness and resilience across all MARL backbones, with the phenomenon also generalizing to robust MARL methods across these backbones. Code and results available at https://github.com/BUAA-TrustworthyMARL/adv_marl_benchmark .

---