Artificial Intelligence · Cross-listed from cs.LG
Uncertainty-aware reinforcement learning for chemical language models
Borja Medina and Jon Paul Janet
Reinforcement Learning (RL) has become a powerful paradigm for de novo molecular design, enabling Chemical
Language Models (CLMs) to navigate and explore the chemical space while optimizing specific desired properties. However, the existing RL frameworks treat all scoring functions as deterministic oracles, neglecting the inherent uncertainty attached to the predictions of the different molecular properties. This can lead to the exploration of highly-uncertain regions of the chemical space, focusing on the generation of highly scored molecules which are poorly supported by the training data. This can destabilize the optimization process, yielding predictions that are far from their true values. We propose and compare two complementary ways of incorporating predictive uncertainty into RL. In the first one, uncertainty is treated as an additional optimization objective and incorporated along with the rest of the scoring functions, allowing the policy to trade off exploitation against reliability. Secondly, uncertainty is used to modulate policy updates, reducing the influence of molecules whose properties lie far outside the scoring function confidence domain. Both approaches were evaluated across three different settings: (i) a controlled model system, in which the prediction error is modeled as a Gaussian distribution, with a variance proportional to the distance to the training data; and two real-world tasks, making use of (ii) ChemProp models and (iii) a Conformal Prediction wrapper applied to a Random forest classifier. We show that uncertainty-aware RL enables CLMs to explore chemical space more robustly by favoring lower-uncertainty regions. This leads to more reliable hit discovery without compromising molecular score, increasing the true hit rate by 0.25 (from 0.5 to 0.75), and nearly doubling the total number of true hits.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
When Multi-Sensor Fusion Fails to Generalize: Cattle Posture Classification Under Animal-Level and Temporal Distribution Shift
Leutrim Uka, Severino Pinto, Gundula Hoffmann et al. (+1 more)
Automated cattle posture-classification systems frequently report near-perfect accuracy, yet their robustness under realistic deployment conditions remains largely unknown. In particular, it is unclear whether
multimodal sensor fusion improves generalisation or leads models to rely on context-specific signals that fail under distribution shift. Here, we evaluate the robustness of automated posture classification (lying versus standing) using collar accelerometers, rumen-bolus sensors, and environmental measurements collected from a pasture-based beef cattle herd across two consecutive years (2024-2025). XGBoost served as the primary model, with Logistic Regression, Random Forest, and Long Short-Term
Memory networks evaluated as comparative baselines. Model robustness was assessed under progressively more stringent evaluation protocols, ranging from conventional random train-test splits to leave-one-animal-out validation and cross-year evaluation on an independent cohort of previously unseen animals recorded one year later. While
multimodal models achieved strong within-year performance (macro-F1 0.94), the performance declined substantially under cross-year evaluation (macro-F1 0.49). Explainability analysis revealed persistent reliance on rumen-bolus activity and environmental variables even when predictive performance deteriorated. Distribution-shift diagnostics further confirmed substantial differences in feature distributions between recording years. Our findings demonstrate that commonly used evaluation protocols can substantially overestimate real-world performance and that
multimodal sensor fusion may reduce, rather than improve, robustness under temporal distribution shift. More broadly, the results highlight that
benchmark accuracy alone is insufficient to assess deployment readiness and underscore the need for robustness-centred evaluation in livestock-monitoring research.
Read the full abstract ▾
All authors Leutrim Uka, Severino Pinto, Gundula Hoffmann, Marina M.-C. Höhne
Artificial Intelligence · Cross-listed from cs.LG
Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection
Louis Simon and Mohamed Chetouani
Personalization in wearable-based stress detection remains challenging due to substantial inter-individual variability in physiological and behavioral responses. While traditional approaches rely on user-specific fine-tuning or costly self-supervised pre-training on large
datasets, we propose a lightweight alternative based on
retrieval-augmented personalization. Our method leverages frozen, out-of-domain foundation models to retrieve similar patterns from a target user's history and encode them into a compact personalized
embedding that modulates representations extracted by a lightweight
transformer network. We evaluate our approach on the WESAD stress detection
dataset with N=15 users, comprising wrist-worn physiological (EDA, BVP, temperature) and activity (accelerometer) signals, and report gains of +3.92% in accuracy and +4.76% in macro F1-score over a non-personalized
transformer baseline, approaching supervised fine-tuning performance without requiring any labeled user data. We further show that temporal
retrieval, where only prior user samples are available, achieves performance close to full intra-user
retrieval, demonstrating robustness to limited user history. Finally, we explore personalization in a cross-
dataset retrieval setting, leveraging
embeddings from the K-Emocon
dataset to personalize representations for stress detection on the WESAD
dataset.
Read the full abstract ▾
Artificial Intelligence
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
Sana Ayromlou, Purvi Sehgal and Pradyumna Narayana
Foundation-model
agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories. While Multi-
Agent Debate (MAD) succeeds in deterministic domains,
agents in subjective tasks like persuasion experience severe problem drift and sycophantic conformity. We identify semantic leakage in standard
Retrieval-Augmented Generation (RAG) as a reproducible trigger for these failures, as standard RAG prioritizes vocabulary overlap over logical necessity. To eliminate this leakage, we introduce Taxonomic Strategy RAG (TS-RAG), a systems intervention that routes strategies through a discrete categorical bottleneck to decouple argumentative structure from topical content. Zero-shot, cross-domain evaluations demonstrate that TS-RAG significantly improves the transfer of abstract logic where standard semantic
retrieval collapses. Crucially, TS-RAG acts as a "capability bridge" in asymmetric deployments, empowering lightweight persuaders to consistently defeat parametrically superior opponents (improving win rates from 70.5 to 78.5) and accelerating argumentative efficiency. Finally, we introduce trace-level diagnostics via a turn-by-turn Debate State Representation (DSR), demonstrating the necessity of strict constraints to prevent evaluation collapse via default agentic sycophancy.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Why Do Accumulated Transformations Extrapolate?
Mahesh Godavarti
PaTH
Attention showed that replacing RoPE's position-indexed rotations with accumulated data-dependent Householder reflections yields strong length extrapolation, though performance degrades at extreme context lengths. We ask whether this depends on Householder-specific structure or reflects a general property of accumulated transformations along source-to-query paths. We study a simpler variant keeping RoPE's block-diagonal SO(2) rotations but replacing position-indexed angles with accumulated
token-dependent ones. It shows the same pattern: improved extrapolation then degradation at long contexts. We prove the result extends to accumulated orthogonal transformations satisfying certain regularity conditions: their products become incoherent after finitely many steps, suppressing
attention to distant
tokens. Accumulated rotations of queries and keys create a finite mixing window independent of context length; per-
token suppression learned in training transfers unchanged to any evaluation length, and high-dimensional concentration produces a score gap suppressing far
tokens while near-route transport preserves the target signal. Conversely, a lower bound shows accumulated rotations must eventually degrade: as the far set grows, no rotations preserve the near signal without explicit far-mass control. For SO(2) rotations, rotating values too makes residual far contributions combine incoherently, extending the range. Controlled experiments support these predictions: random accumulated rotations substantially improve extrapolation over RoPE, learned
token-dependent rotations maintain near-training-length perplexity far beyond the training context, and rotating values helps over queries and keys alone. Rotation-only models still degrade at extreme lengths, while ALiBi stays length-stable, consistent with the need for far-mass control.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Quantifying Explainable AI-introduced signal noise on ECG data with Spectral Entropy
David A. Kelly and Nathan Blake
Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be trusted and decisions justified. Explainability (XAI) tools use heuristics which often add signal noise to the explanation "core". It is not always obvious what is signal from the model and what is noise from the XAI. We propose the use of spectral
entropy as a measure of noise in XAI output. We demonstrate its usefulness in the context of classifying arrhythmias in an ECG
dataset with different post hoc explainability techniques.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
LLM Performance on a Real, Double-Marked GCSE Benchmark
Malachy Fox, Kavi Samra and Paul Jung
We introduce a
dataset of 32,534 double-marked real student responses to GCSE mock exams (GCSEs are the UK's national exams, taken at age ~16), spanning 328 questions across five subjects and including handwritten work. We test whether off-the-shelf large
language models agree with examiners as closely as the two examiners agree with each other. We find that models overwhelmingly agree well with the examiner consensus across subjects, with the top performing models agreeing more closely with examiners than examiners agree with each other. Models achieve high scores for subjective tasks like English essay marking, as well as handling complex and messy handwritten Maths paper scripts. Agreement is uniform near the examiner line, and not massively discriminated by model size, providing cost-effective automated marking solutions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Geological text descriptions in ill-posed inverse problems: insights from learned hydraulic-conductivity inversion
Taiga Saito, Yu Otake, Daijiro Mizutani et al. (+1 more)
Hydraulic-conductivity inversion is ill posed: even complete head observations can leave structural ambiguity. Geological text descriptions can supply additional information about subsurface structure to constrain reconstruction. However, it remains unclear when descriptions improve reconstruction and how solvers use their stated content. We examine these questions in learned inversion using a synthetic Darcy-flow
dataset with idealised descriptions, varying observation density and flow direction. After sparse-observation training, descriptions can improve reconstruction over models trained without them when observations leave structural ambiguity, though gains vary across conditions and runs. Instance-specific content can improve reconstruction beyond field-type information. Editing this content shifts reconstructions toward the stated geometry of selected features, less strongly as observations become more informative about those features. We do not establish a reconstruction advantage of text over numerical inputs encoding the same geological information. Finally, we discuss how this complementarity could guide the joint design of measurements and geological knowledge acquisition in site investigations.
Read the full abstract ▾
All authors Taiga Saito, Yu Otake, Daijiro Mizutani, Sopheakpolin Mom
Artificial Intelligence
Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners
Anirban Das, Joanne Boisson, Irtaza Khalid et al. (+2 more)
Reasoning about relational structures remains a significant challenge for neural models, particularly when they must systematically apply learned knowledge to problem instances that are harder than those seen in training. Progress is hampered by the difficulty of evaluating such generalization, since a priori, it is rarely clear what makes an instance hard. We study how this issue can be addressed by using large
language models (LLMs) to automate
benchmark generation, learning to produce increasingly challenging instances in an end-to-end manner. Concretely, given a world parametrized by Datalog rules, and an Edge
Transformer as the
reasoning evaluator, we use LLM-driven evolutionary search (based on FunSearch) and autonomous agentic search to discover sampling functions that yield hard problem instances. We also show that the Edge
Transformer can be improved using this data such that it generalizes well to further data perturbations. Finally, we show that the same machinery can be applied to novel worlds proposed by LLMs, opening the door to autonomous research on neural relational
reasoning.
Read the full abstract ▾
All authors Anirban Das, Joanne Boisson, Irtaza Khalid, Sumita Garai, Steven Schockaert
Artificial Intelligence · Cross-listed from cs.LG
Enhancing Clinician Decision-Making via Uncertainty-Aware Multi-Expert Fusion for Stroke Rehabilitation
Tamim Ahmed and Thanassis Rikakis
Tailoring stroke rehabilitation requires assessing how movements are organized, not merely if they succeed. Currently, this assessment is a rate-limiting bottleneck. Instruments like the Action Research Arm Test (ARAT) compress rich behavioral observations into single ordinal endpoints, discarding the movement-quality details that distinguish recovery from compensation. Automated alternatives typically chase accuracy on noisy, single-observer labels to output opaque scores - a technology-centric approach that rarely reaches clinical practice. To address this, we present xAARA: an engine designed to augment rather than replace clinical judgment. From multi-view
video, xAARA returns ARAT assessments with calibrated uncertainty and explanations across task, movement-phase, and movement-quality levels. Treating clinical scoring as an ill-posed inference problem, xAARA composes 692 calibrated
multimodal models via a Dynamic
Bayesian Network with
entropy-based gating. It qualifies results against clinical validity rules and defers low-confidence cases. In 105 stroke survivors (788 exercises), xAARA achieved 94.2% task accuracy (Cohen's kappa=0.934) and 81.3% movement-phase accuracy (kappa=0.727), reducing predictive uncertainty by 96.1% compared to single-clinician scoring. For subjective cases, it matched at least one rater 100% of the time and never returned out-of-range scores. Four independent clinicians validated the assessments and indicated willingness to adopt the system. We argue that principled uncertainty quantification and clinician-aligned explainability are the critical bridges moving automated assessment from technical demonstration to a deployable clinical tool.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Reliable Conformal Prediction for Ordinal Classification Using the Ranked Probability Score
Stefan Haas, Luca Killmaier, Alireza Javanmardi et al. (+1 more)
Ordinal classification (OC) arises in high-stakes domains such as medicine and finance, where uncertainty quantification must account for the severity of ordinal errors. Conformal prediction (CP) provides distribution-free prediction sets with marginal coverage guarantees; however, its practical effectiveness depends critically on the choice of nonconformity function. We introduce a CP method for ordinal classification based on the ranked probability score (RPS), a proper scoring rule defined over cumulative predictive distributions. Although it reflects ordinal risk quite naturally, it has largely been neglected in conformal ordinal prediction (COP). When used as a measure of nonconformity, RPS yields median-centered contiguous prediction sets by construction. The method is model-agnostic, supports both assessed and grouped ordered categorical outcomes, and permits efficient implementation compared to greedy interval selection procedures. Across multiple ordinal image and tabular
datasets, RPS-based CP produces contiguous prediction sets and strikes a favorable balance between prediction set width and the magnitude of ordinal miscoverage relative to existing CP methods.
Read the full abstract ▾
All authors Stefan Haas, Luca Killmaier, Alireza Javanmardi, Eyke Hüllermeier
Artificial Intelligence · Cross-listed from cs.LG
Convex–Concave Quadratic Spectral Filtering for Graph Neural Networks
Ranhui Yan, Jia Cai, Mengzhu Chen et al. (+1 more)
Spectral graph neural networks (GNNs) interpret message passing as frequency-selective filtering. While low-order spectral filters are efficient, their limited selectivity often leads to weak attenuation outside the passband, whereas high-order alternatives introduce optimization challenges. We propose DCQ-GNN, a spectral GNN based on a compact bank of adaptive convex–concave quadratic filters. By restricting the filter order to two while explicitly exploiting complementary
curvature, DCQ-GNN improves spectral selectivity as quantified by Dirichlet energy and
entropy measures without resorting to high-order
polynomial expansions. The model fuses filter outputs through a node-adaptive gating mechanism to enable node-wise structure-aware spectral selection. We provide a formal spectral analysis grounded in Dirichlet energy attenuation, von Neumann
entropy, and
curvature polarity, and derive explicit characterizations of filter behavior across varying levels of homophily and structural perturbations. Extensive
benchmarks on 10
datasets show that DCQ-GNN ties for the top average rank (3.0) on heterophilic graphs and obtains the second-best rank (4.2) on homophilic graphs, remaining competitive with representative high-order
polynomial spectral filters. Furthermore, under strong structural perturbations, DCQ-GNN exhibits substantially smaller performance degradation compared to both first-order and high-order baselines. These results demonstrate that
curvature-aware quadratic banks provide a robust and efficient alternative to high-order spectral models while preserving optimization stability and computational efficiency.
Read the full abstract ▾
All authors Ranhui Yan, Jia Cai, Mengzhu Chen, Haodong Yang
Artificial Intelligence · Cross-listed from cs.CL
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
Cosimo Galeone, Anna Ettorre, Minsu Park et al. (+2 more)
A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it. This rests on a hidden premise – that the direction which detects a behavior and the direction which controls it are the same, or close. We test this geometrically: what is the angle between the direction that best detects a behavior and the one that best causes it? If detection implies control the cosine is near 1; otherwise it quantifies a detection-intervention gap. On Gemma 2-2B-it, output format (clean JSON vs markdown fencing) collapses both roles onto one axis.
Hallucination does not: the model detects fake entities with perfect linear separability (AUC = 1.000 from layer 5), yet that direction sits at cos = 0.12 (about 83 degrees) from the direction producing a refusal – a small, reproducible
alignment, far from the cos = 1 that "detection is control" would require. A detector built from activations, with no chosen
tokens, likewise fails to align (cos = -0.06). The gap generalizes: across four models from three families and two scales (1B-9B), cos stays in [0.12, 0.20], identical before and after instruction tuning (0.1197 vs 0.1200), placing its origin in pretraining. A 15-degree rotation toward the refusal direction partially bridges it – 73% and 60% refusal on two held-out fake-entity categories at 1.8% false positives. We then ask whether this cosine predicts steerability, and it does not: detection is a high-dimensional class, not a single direction, and what separates the steerable case is functional, not readable from a static angle. The cosine is a weight-computable signature of the dissociation between knowing and steering, not a predictor of it.
Read the full abstract ▾
All authors Cosimo Galeone, Anna Ettorre, Minsu Park, Giuseppe Ettorre, Daniele Ligorio
Artificial Intelligence · Cross-listed from cs.LG
MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios
Patara Trirat, Jin Myung Kwak, Jay Heo et al. (+2 more)
Financial decision-making is contextual:
forecasting prices, valuing companies, and assessing event exposure weigh price history, accounting fundamentals, macroeconomic regime, and contemporaneous text. A
benchmark over these four signals is hard to build because finance violates four assumptions of time-series evaluation: text must be gated by its publication date to prevent look-ahead, quarterly fundamentals are reported with a one- to ninety-day lag, filing text is partly redundant with the numerical statement fields it accompanies, and macroeconomic regimes leak across calendar splits. No public
benchmark addresses all four signals jointly. MacroLens covers 4,416 U.S. small- and micro-cap equities over 2021-2026. Seven tasks share one point-in-time panel of prices, 46.8M XBRL accounting facts, 53 macroeconomic series, 295,860 SEC filings, and 215,882 news articles, plus a scenario layer of 1,130 macroeconomic events across 49 types automatically detected and rendered as natural
language. Tasks span contextual
forecasting, public and private valuation, statement generation from fundamentals and descriptions, scenario-conditioned returns, and real-estate valuation. We evaluate 19 methods across six families spanning naive heuristics through time-series foundation models, fine-tuned LLM-based time-series models, and zero-shot large
language models (LLMs), plus a five-step feature-context ablation on two frontier LLMs and a gradient-boosted baseline. MacroLens is released at https://huggingface.co/
datasets/DeepAuto-AI/MacroLens.
Read the full abstract ▾
All authors Patara Trirat, Jin Myung Kwak, Jay Heo, Heejun Lee, Sung Ju Hwang
Artificial Intelligence · Cross-listed from cs.SD
What Does a Pathological Speech Assessment Model Know about Acoustic Features? A Case Study on Oral and Oropharyngeal Cancer Patients
Tuan Nguyen, Corinne Fredouille, Alain Ghio et al. (+2 more)
This work investigates the interpretability of a Wav2Vec 2.0based
speech intelligibility assessment model for oral and oropharyngeal cancer patients through canonical correlation analysis. By measuring the correlation between the model
embeddings and eGeMAPS low-level descriptors (LLDs) as an interpretable reference, we analyze how acoustic information is encoded across the model layers. The analysis is conducted at two levels: individual LLDs layer-wise, and group-level: prosodic, spectral, and voice quality. Results show that the learned representations are most strongly correlated with spectral and prosodic features, with the first MFCC coefficient yielding the highest correlations across all layers. At the group level, spectral and prosodic groups achieve correlations of 0.77 and 0.71 respectively, while voice quality reaches 0.65. Beyond model interpretability, this work also offers practical guidance on acoustic feature selection for pathological
speech assessment.
Read the full abstract ▾
All authors Tuan Nguyen, Corinne Fredouille, Alain Ghio, Muriel Lalain, Virginie Woisard
Artificial Intelligence · Cross-listed from cs.LG
Holographic Memory for Zero-Shot Compositional Reasoning in Knowledge Graphs: A Mechanistic Study of Where and Why It Fails
Randhir Kumar
Knowledge graph
embedding (KGE) models predict single-hop links well but have no mechanism for zero-shot compositional queries: multi-hop questions whose relation chains never appeared during training.
Holographic Reduced Representations (HRR), which bind and unbind symbols via circular convolution, are a theoretically attractive candidate, since binding is approximately invertible and associative. We test whether this promise holds. We study two
holographic memory variants, real-valued HRR and phase-only
Fourier HRR (FHRR), each with a modern Hopfield cleanup, on FB15k-237 over five seeds. Four findings follow. First, both are competitive single-hop retrievers (filtered MRR 0.358 +/- 0.002 for HRR, 0.350 +/- 0.021 for FHRR). Second, neither composes zero-shot: accuracy stays at chance across all cleanup temperatures. Third, the main contribution, we localise the failure mechanistically. A hop-1 probe shows the
memory recovers the correct intermediate entity with high fidelity (MRR 0.896 +/- 0.002 for HRR), yet composition still fails even with a verified-correct intermediate. A second probe shows why: posing the ground-truth second-hop fact as a standalone atomic query, bypassing composition entirely, already recovers it at only 0.26 to 0.48x average atomic accuracy, uniformly across relation fan-out. The bottleneck is not the bind-unbind
algebra or the cleanup; it is that facts compositional chains pass through are intrinsically harder for the superposed
memory to retrieve, a capacity and interference effect present already at a single hop. Fourth, we prove (Lemma 4.1) that FHRR's softmax cleanup is not phase-equivariant, compounding the primary failure on the minority of chains where hop-1 itself errs. Fixing zero-shot composition requires improving
retrieval capacity under superposition, not just redesigning the cleanup.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
InSight: Self-Guided Skill Acquisition via Steerable VLAs
Maggie Wang, Lars Osterberg, Stephen Tian et al. (+5 more)
Vision-
language-action (VLA) models excel at
robot manipulation via imitation learning, but adapting them to new tasks often requires additional human demonstrations, which can be costly or infeasible. Meanwhile,
vision-
language models (VLMs) offer semantic task understanding but lack the physical grounding required for execution. To bridge this gap, we present InSight, a framework for self-guided skill acquisition that uses a VLM to identify primitives missing from a VLA's repertoire, grounds the VLM's proposals through
robot execution, and distills new primitives from successful rollouts into the VLA. Primitive steerability, the ability to execute and terminate primitives on command, enables the
robot to reuse known primitives while collecting training data for missing primitives without requiring full-task human demonstrations for each new task. InSight has two stages: (1) a VLM automatically segments existing demonstrations into primitive-labeled trajectories to fine-tune a primitive-steerable VLA, and (2) the VLM plans a sequence of known primitives executed by the VLA and new primitives attempted by VLM-parameterized low-level controllers. New-primitive segments from successful task rollouts are added to the training data, and the VLA is retrained. The adapted VLA can then reliably execute new skills using the acquired primitives, without per-primitive VLM calls. We evaluate InSight on six simulated and real-world tasks with no human demonstrations of target skills, including block flipping, drawer closing, sweeping, twisting, and pouring. On hardware, acquired twisting and pouring skills achieve 92% and 96% success, versus 32% and 16% for a zero-shot CaP-X baseline. Composing both skills into a 14-primitive task achieves 80% success with no combined-task demonstrations. Project website: https://insight-vla.github.io/ .
Read the full abstract ▾
All authors Maggie Wang, Lars Osterberg, Stephen Tian, Ola Shorinwa, Joseph Bowkett, Daniel Pastor, Jiajun Wu, Mac Schwager
Artificial Intelligence · Cross-listed from cs.CV
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Haorui Ji, Weizhe Liu, Hongdong Li et al. (+1 more)
Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two structural bottlenecks. First, they adopt discriminative 2D features optimized for semantic abstraction to construct sparse voxel latents, which suppress reconstructive cues and induce a representation bottleneck. Second, in the generation stage, standard
diffusion transformers lack effective mechanisms to align dense 2D image
tokens with sparse 3D voxel latents, resulting in a cross-modal correspondence bottleneck. To address these issues, we propose FLUX3D, a scalable image-to-3DGS framework that boosts both representation learning and cross-modal
alignment during generation. We first revisit 2D feature selection for sparse-voxel-based 3D representation learning, propose
Diffusion-Aligned Structured Latents (DA-SLAT) and couple it with a decoder-only architecture to improve 3DGS reconstruction fidelity. We also design a sparse-structure-aware
diffusion framework, which integrates the Sparse-structure
Multimodal Diffusion Transformer (SMDiT) and Modal-Aware Rotary Positional
Embedding (MARoPE) to achieve geometry-agnostic 2D-3D
alignment. Extensive
benchmark experiments demonstrate that FLUX3D yields substantial improvements in appearance fidelity and significantly outperforms all state-of-the-art (SOTA) methods in generating high-quality 3DGS assets.
Read the full abstract ▾
All authors Haorui Ji, Weizhe Liu, Hongdong Li, Hengkai Guo
Artificial Intelligence
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina et al. (+47 more)
Agentic
language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable
agents. Existing open efforts such as SWE-Smith, SERA, and Nemotron-Terminal typically target a single
benchmark, leaving open the question of how to train models that generalize across diverse agentic tasks. The OpenThoughts-
Agent (OT-
Agent) project addresses this gap with a fully open data curation pipeline for training agentic models. We conduct more than 100 controlled ablation experiments to systematically investigate each stage of the pipeline, yielding insights on the importance of task sources and diversity. We then assemble a training set of 100K examples from our pipeline and fine-tune Qwen3-32B on this
dataset, which yields an average accuracy of 44.8% across seven agentic
benchmarks and a 3.9 percentage point improvement over the strongest existing open data agentic model (Nemotron-Terminal-32B, 40.9%). Moreover, our training data exhibits strong scaling properties, outperforming alternative open
datasets at every training set size in compute-controlled comparisons. We publicly release our training sets, data pipeline, experimental data, and models at openthoughts.ai to support future open research on agentic model training.
Read the full abstract ▾
All authors Negin Raoof, Richard Zhuang, Marianna Nezhurina, Etash Guha, Atula Tejaswi, Ryan Marten, Charlie F. Ruan, Tyler Griggs, Alexander Glenn Shaw, Hritik Bansal, E. Kelly Buchanan, Artem Gazizov, Reinhard Heckel, Chinmay Hegde, Sankalp Jajee, Daanish Khazi, Emmanouil Koukoumidis, Xiangyi Li, Hange Liu, Shlok Natarajan, Harsh Raj, Nicholas Roberts, Ethan Shen, Nishad Singhi, Michael Siu, Ashima Suvarna, Hanwen Xing, Patrick Yubeaton, Robert Zhang, Leon Liangyu Chen, Xiaokun Chen, Steven Dillmann, Saadia Gabriel, Xunyi Jiang, Anurag Kashyap, Boxuan Li, Yein Park, Minh Pham, Sujay Sanghavi, Lin Shi, Ke Sun, Yixin Wang, Zhiwei Xu, Erica Zhang, Siyan Zhao, Wanjia Zhao, Jenia Jitsev, Alex Dimakis, Benjamin Feuer, Ludwig Schmidt
Artificial Intelligence · Cross-listed from cs.HC
It's Complicated: On the Design and Evaluation of AI-Powered AAC Interfaces
Blade Frisch, Will Wade, Dylan Gaines et al. (+4 more)
Artificial intelligence (AI) can enhance what people who use augmentative and alternative communication (AAC) are able to do with their systems. However, evaluating AI-powered AAC interfaces can be difficult. People are intersectional beings and current evaluation metrics can struggle to capture the multifaceted and nuanced desires people may have for their AAC. We explore the complicated nature of six AAC problem spaces, explore how AI might be used in these spaces, and suggest more robust methods of evaluation that take the intersectional nuances of people into account. We also discuss broader issues that arise across these problem spaces and how they could be addressed using our proposed evaluation methods.
Read the full abstract ▾
All authors Blade Frisch, Will Wade, Dylan Gaines, Michelle Kinsella, Betts Peters, Tamara Broderick, Keith Vertanen
Artificial Intelligence · Cross-listed from cs.CV
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Zixuan Li, Haokun Lin, Yicheng Xiao et al. (+10 more)
Unified multi-modal large
language models (MLLMs) have achieved strong text-to-image generation quality, but still struggle with structure-aware
prompt following, where object counts, spatial relations, attribute bindings, and coarse layouts must be preserved. We attribute this limitation in part to the
entanglement of structural planning and appearance rendering within a single conditioning stream. To address this issue, we propose Implicit Visual Chain-of-Thought (IV-CoT), a latent visual
reasoning framework for query-conditioned image generation. IV-CoT decomposes the visual conditioning queries into a structural-to-semantic cascade, where structural queries first form a latent visual plan and semantic queries then render appearance conditioned on this plan. To guide the structural queries, we introduce training-only sketch supervision, which encourages them to capture structure from sketches without requiring sketch extraction or intermediate decoding at inference time. IV-CoT performs implicit CoT
reasoning in a single forward pass and achieves superior results on GenEval and T2I-CompBench. Visualizations and analyses demonstrate that the learned structural and semantic queries play complementary roles in structure-aware generation.
Read the full abstract ▾
All authors Zixuan Li, Haokun Lin, Yicheng Xiao, Zhiwei Li, Xinyang Song, Zelong Zheng, Yong He, Heng Yao, Ke Ding, Chao Yu, Chuan Yuan, Qi Li, Zhenan Sun
Artificial Intelligence
World Models in Pieces: Structural Certification for General Agents
Yikai Lu, Yifei Wu, Xinyu Lu et al. (+1 more)
In the big-world regime,
agents cannot be universally capable and their ability is inevitably specialized across a world model in pieces. Consequently, standard uniform guarantees fail to distinguish between the understanding of critical bottlenecks and irrelevant failures. We first formalize this limitation by proving that general
agents are not universal, rendering standard worst-case analysis uninformative. To overcome this, we introduce structural certification, a transition-local framework that maps bounded goal-conditioned performance to entry-wise guarantees on the
agent's internal world model. Our main contribution is constructive. We provide
algorithms that filter specific transitions using deep compositional goals and prove that a general
agent on these goals has a structural world model with a $\mathcal{O}(1/n) + \mathcal{O}(\delta)$ error bound. Conversely, this bound is tight in the small-$\delta$ regime, whose existence is explicitly guaranteed by our certification. These results enable the certifiable deployment of general
agents by localizing the specific transitions where long-horizon planning is reliable.
Read the full abstract ▾
All authors Yikai Lu, Yifei Wu, Xinyu Lu, Tongxin Li
Artificial Intelligence
Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models
Ahmad Pouramini and Hesham Faili
Prompt-based learning has emerged as a dominant paradigm in natural
language processing. This study explores the impact of diverse pre-training objectives on the performance of encoder-decoder pre-trained
language models across generation and question answering tasks, with a focus on commonsense knowledge
retrieval and completion. We highlight the benefits of incorporating multiple objectives during both pre-training and fine-tuning stages. We introduce the Match Task to Objective (MTO) framework and methods for determining the appropriate objective for a given task. This framework offers automated methods to prepare task-related data for adaptation through unsupervised training, based on the identified objective. In the fine-tuning stage, we design novel templates that align with the objectives of the pre-training and adaptation stages. When aligned with task requirements, these strategies can achieve a performance gain of over 120% compared to conventional methods in few-shot settings. They significantly outperform related works in few-shot settings and exceed the baseline even in full-
dataset scenarios. Furthermore, we extend this approach to include
prompt-tuning methodologies, providing guidance for more effective soft
prompt engineering and optimization. Our strategies significantly enhance
prompt-tuning performance as well. These insights hold substantial value, precisely guiding the selection and optimization of models customized for specific tasks. Code is available at https://github.com/puraminy/MTO/
Read the full abstract ▾
Artificial Intelligence
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
Tian Zheng and Kai-Tai Hsu
Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics. This makes them more challenging to evaluate than single-turn LLM responses. It is therefore necessary to distinguish genuine disagreement between an
agent's output and a ground-truth answer from grading artifacts. We investigate how reliably automated graders assess such a system and what strategies improve grading quality by applying LAMBDA, a multi-
agent data-analysis system, on 153 numerical QRData tasks from DSGym. We develop and evaluate a three-layer human-AI grading cascade: strict regex matching, LLM-based lenient grading, and snippet-based human inspection, which combines non-GenAI and GenAI strategies with different failure profiles. Both automated graders achieve 100% observed precision (0/70 false positives). The lenient grader's recall is 97% against human labels. A keyword-anchored extraction pipeline raises the strict grader's recall by 60 percentage points over a last-number heuristic; the lenient grader is architecturally parser-independent. An iterative nudge mechanism raises grading run success from 36% to 97% and lenient-pass rates from 16% to 46%; comparing nudging with and without original-question re-injection shows that re-injection offers no benefit, confirming the nudge as an answer template cue. We further observe in this case study that variable type is the task metadata field most consistently associated with grading pipeline dynamics and observed outcome grades.
Read the full abstract ▾
Artificial Intelligence
Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
Ali Pourghasemi Fatideh, Wilder Baldwin, Maria Dhakal et al. (+2 more)
LLM-based dialogue assistants have become mainstream tools for software developers, yet current evaluation
benchmarks focus exclusively on functional correctness. This leaves a critical gap in assessing the quality and accuracy of these conversations when handling Non-Functional Requirements (NFRs), which are inherently vague, context-dependent, and involve many parts of a program. Evaluating how well these systems support collaborative
reasoning about NFRs requires methods that go beyond single-turn accuracy to capture both the correctness of the system's outputs and the quality of the multi-turn interaction. In this paper, we investigate the accuracy and quality of multi-turn conversations between developers and an LLM-based
agent in the domain of Health Insurance Portability and Accountability Act (HIPAA) regulatory compliance. We hired 49 programmers to interact with GitHub Copilot to assess 148 HIPAA-derived NFRs against the iTrust codebase, a system designed to comply with HIPAA regulations, across three dimensions: requirement satisfaction level,
reasoning, and code localization. We find that developers tend to agree with LLM assessments, but accuracy against expert ground truth is low. We model user satisfaction and find that longer system responses and more information-providing turns negatively affect user satisfaction, whereas proactive interactions positively affect it. Our findings provide insights for designing LLM-based dialogue systems that support NFR assessment.
Read the full abstract ▾
All authors Ali Pourghasemi Fatideh, Wilder Baldwin, Maria Dhakal, Collin McMillan, Sepideh Ghanavati
Artificial Intelligence
Difference-Making without Making a Difference
Sander Beckers
Over a series of seven papers, Andreas & Günther have introduced seven definitions of actual causation and have classified them as belonging to three different, competing, types of accounts: factual difference-making, counterfactual difference-making, and regularity-based. I show that their most recent – factual difference-making – definition instantiates all three types, thereby proving that these are distinctions without a difference. I further compare their novel account to the other six accounts on several crucial examples, revealing that this undermines all seven of their accounts.
Read the full abstract ▾
Artificial Intelligence
Solving Inverse Problems of Chaotic Systems with Bidirectional Conditional Flow Matching
Peiyan Hu, Jian Zhang, Jiashu Pan et al. (+6 more)
Modeling chaotic systems is crucial yet challenging. Inverse problems in chaotic dynamics, namely inferring initial conditions from final states, remain largely unsolved because of ill-posedness, non-uniqueness, instability, and potentially chaotic time-reverse dynamics. We address this open problem with Bidirectional Conditional Flow Matching (Bi-CFM), which learns bidirectional mappings between distributions of initial and final states to capture the stochasticity of chaotic
evolution and mitigate exponential error accumulation over time. Furthermore, for systems with conservation laws, we extend it to Conservation-constrained Bi-CFM (CBi-CFM). Across the classic Lorenz,
Circuit, and high-dimensional Lorenz 96 systems, Bi-CFM improves five distribution-level metrics over baselines while achieving a speedup of more than two orders of magnitude. In the three-body
planet-
planet scattering problem in planetary dynamics, CBi-CFM better respects conservation laws, with conservation errors comparable to those of the ground truth. Finally, on real observations of globular clusters, collisional million-body systems shaped by $\sim 10^{10}$ years (10 Gyr) of
evolution, our method represents an advance in accuracy, establishing a scalable route to solving inverse problems of long-timescale real-world chaotic dynamics.
Read the full abstract ▾
All authors Peiyan Hu, Jian Zhang, Jiashu Pan, Ruiqi Feng, Tao Zhang, Zhi-Ming Ma, Yuan-Sen Ting, Gongjie Li, Tailin Wu
Artificial Intelligence · Cross-listed from quant-ph
Large-Language-Model Discovery of Quantum LDPC Codes through Structured Concept Evolution
Zidu Liu and Florian Marquardt
Quantum low-density parity-check codes promise low-overhead error correction, but high-performing constructions remain hard to find. Here we introduce structured concept
evolution, in which a large
language model (LLM) evolves construction programs and their internal search strategies by modifying the finite group, protograph shapes or entry-assignment rule. We search for codes with fewer than $600$ data
qubits and check weight at most $12$, optimizing $kd^2/n$ or the
circuit-level logical error rate. Our method improves on published lifted-product
benchmarks in selected parameter regimes, with exactly certified distances for the leading results.
Circuit-level optimization typically yields lower logical error rates than $kd^2/n$ optimization, often despite smaller code distances. With the same
evolution framework and step budget, the best LLM outperforms all random-mutation and hill-climbing runs on both objectives. Our results point to LLM-driven program search as an approach to designing general
quantum LDPC codes.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
Chenrui Fan and Paolo Favaro
Generic text-to-
video models can be used as rich open-world scene priors. Despite the high quality of today's generated
videos, they do not directly yield reliable 3D assets: camera motion is difficult to control, view coverage is partial, and frames often contain inconsistencies across time. We introduce OrbitForge, an adapter built from frozen
video priors and per-
prompt Gaussian Splatting reconstruction optimization that converts a single text-generated
video into a canonical closed-orbit 3D Gaussian Splatting scene. We use 3D reconstruction as an anchor to improve the 3D consistency of the generated
video. We obtain a preliminary 3D reconstruction from a first generated
video via Deformable Gaussian Splatting with a robust MedianGS proxy. We render views from a prescribed orbit to detect missing viewpoints. OrbitForge uses the text-to-
video model to complete only the missing views, and reconstructs the completed orbit into a final Gaussian Splatting scene. This design requires no task-specific
video or multiview fine-tuning, avoids per-
prompt score-
distillation optimization, and does not progressively generate views one step at a time. We further argue that this setting demands coverage-aware evaluation: local smoothness alone rewards methods that never attempt a full orbit. On a frozen 300-
prompt T3Bench-derived audit, OrbitForge reconstruction attains a 359.0-degree measured median span, raises originally unsupported-bin Q10 ImageReward from 8.07 to 16.36 relative to MedianGS-only reconstruction, while remaining competitive with VideoMV on the coverage-quality.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
EG-VQA: Benchmarking Verifiable Video Question Answering with Grounded Temporal Evidence
Linpeng Huang, Weixing Chen, Zexin Chen et al. (+2 more)
Recent advances in
Video Large
Language Models (
Video-LLMs) have yielded promising performance on
Video Question Answering (VideoQA). Nevertheless, existing
benchmarks are predominantly evaluated through answer correctness, while the faithfulness of predicted evidence supporting those answers remains insufficiently evaluated. This disconnect between answer generation and evidence verification motivates the construction of the Evidence-Grounded
Video Question Answering
Benchmark (EG-VQA), a large-scale open-ended
benchmark in which each QA pair is annotated with temporally localized textual evidence, requiring models to jointly produce answers and verifiable evidence. EG-VQA comprises 2,067
videos and 11,838 QA pairs with fine-grained evidence annotations. To evaluate predicted evidence, Evidence-Grounded F1 (EG-F1) is introduced as a metric that jointly measures temporal
alignment and semantic consistency between predicted and ground-truth evidence. Experiments reveal a substantial discrepancy between answer correctness and evidence faithfulness: even strong proprietary models can achieve high answer accuracy while exhibiting gaps in temporal-semantic grounding. To investigate evidence-aware learning under EG-VQA, we develop EG-Reasoner, an evidence-aware model trained with explicit evidence supervision. EG-Reasoner achieves strong evidence grounding performance among open-source models while maintaining competitive answer generation results compared with proprietary systems. These findings highlight the importance of explicitly modeling evidence grounding and suggest that evidence-aware supervision provides an effective direction toward more reliable and interpretable VideoQA systems.
Read the full abstract ▾
All authors Linpeng Huang, Weixing Chen, Zexin Chen, Yang Liu, Liang Lin