Computation and Language
Stranger, Fan, or Peer? A Systematic Study on the Role of Interlocutor in Persona-Based Dialogue Generation
Daniela Occhipinti, Malvina Nissim and Marco Guerini
Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whose biography can vary across training, inference, and evaluation. Prior work often neglected these aspects, obscuring mechanisms that only appear when biography visibility is toggled separately across training, inference, and evaluation, a three-stage factorisation that prior work has largely treated as a single factor. We study this factorisation on a
dataset of dialogues paired with speaker's biographies, varying whether the target and interlocutor speakers see each other's biographies during training and inference, and using an LLM as a judge to perform author identification. We find that (i) training-time visibility, more than inference-time visibility, determines whether models express persona traits through dialogue or fall back on copying biographical text (a known problem/phenomenon in persona-based generation); (ii) models trained with interlocutor-biography visibility copy less target-biographical text than models trained without it, while changing visibility only at inference time has a less consistent effect; and (iii) under asymmetric disclosure, where only the interlocutor sees the target biography, target content leaks into interlocutor turns more often, and dialogues containing such traces are easier for the judge to identify, especially when interlocutor turns are visible. These results suggest that biography leakage into generated turns is an artefact of how interlocutor visibility is configured across training and inference, and separating the three stages is necessary.
Read the full abstract ▾
Data Structures and Algorithms
Tight Bounds for Memory Allocation With and Without Request Fragmentation
Michael A. Bender, Alex Conway, Martín Farach-Colton et al. (+3 more)
The classical
memory-allocation problem captures the task of placing objects of different sizes in
memory, while minimizing the so-called
memory high-water mark. It has been known since the early 1970s that the optimal competitive ratio for any deterministic online allocator is $\Theta(\log M)$, where $M$ is the volume high-water mark of the underlying request sequence. This paper begins with a simple observation: many real-world allocators seem to bypass the 1971 lower bound by adopting a slightly different model for
memory allocation. These allocators use what we call $k$-aggregate request fragmentation, meaning that the
memory allocator is permitted to break requests into multiple fragments, so long as the all-time maximum number of simultaneous fragments is at most $k$ times the all-time maximum number of simultaneous requests. We consider the following basic question: Does request fragmentation fundamentally change the problem of
memory allocation, and if so, how? Our results come with several surprises. Among these, we find that even using $k = 1 + o(1)$ request fragmentation, the optimal competitive ratio—which was $\Theta(\log M)$ in the classical setting—collapses to $\Theta(\log \log M)$. This result is shown to be tight with matching upper and lower bounds, applying to both deterministic and randomized
algorithms.
Read the full abstract ▾
All authors Michael A. Bender, Alex Conway, Martín Farach-Colton, Hanna Komlós, William Kuszmaul, Nicole Wein
Computer Vision
Anatomy-Aware Promptable Segmentation with Online Interactive Training for AUTOPET V
Pablo Lozano-Jimenez, Sergio Romero-Tapiador and Ruben Tolosana
We present an anatomy-aware, promptable model for whole-body lesion
segmentation in FDG and PSMA PET/CT, developed for the AUTOPET V challenge. The proposed method is built as family of nnU-Net-based models and trained in two stages: i) a pre-training stage that produces a strong initial
segmentation, and ii) an online interactive stage that learns to exploit scribble
prompts, refining the prediction over successive interactions. Anatomical context is incorporated through organ supervision using a single shared head that predicts lesions and organs from the same features, which reduces false positives arising from physiological uptake. Also as the tracer (i.e., FDG/PSMA) is not provided at inference, we add a tracer classifier based on image processing and a random forest over coronal MIP features, routing each study to a combined FDG+PSMA model or to a PSMA-specific model. Across four-fold cross-validation the organ-supervised model achieves the best and most stable performance, the interactive stage improves the Dice score monotonically with each
prompt, and PSMA-specific training yields the strongest tracer-wise results.
Read the full abstract ▾
Computer Vision
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
Yixuan Ding, Jiahao Kong, Wei Huang et al. (+2 more)
Autoregressive
video diffusion enables scalable long-
video generation by producing chunks from a bounded recent context. While recency-based caching preserves local continuity, it evicts historical cues needed when subjects, objects, scenes, or attributes reappear. Existing
memory mechanisms expose models to nonlocal history, but access alone does not ensure effective use. Our analysis reveals that
video DiT layers exhibit distinct preferences for current, recent, and distant context, suggesting that long-range
memory requires deciding both what to retrieve and where to use it. We introduce LayerRecall, a current-conditioned, layer-selective
memory router that retrieves relevant historical K/V states and injects them only into backbone-specific
memory-sensitive layers while preserving local
attention elsewhere. To reduce reliance on scarce high-quality long-horizon
videos and explicit
memory-allocation labels, we further propose Cross-Horizon Prediction Matching (CHPM), which uses a privileged long-context reference to supervise the bounded-
memory router in prediction space. Across 100 multi-shot evaluation
prompts, LayerRecall achieves the best overall results on MemoBench and MovieBench while matching its backbone on VBench-Long, demonstrating stronger long-range recovery without sacrificing local continuity. Qualitative analyses further reveal
memory-guided self-correction, whereby initially mismatched local attributes return to their historical appearance without resetting ongoing motion or scene structure. Additional analyses show cross-backbone portability and negligible inference overhead.
Read the full abstract ▾
All authors Yixuan Ding, Jiahao Kong, Wei Huang, Ruijie Quan, Yi Yang
Computation and Language
Acquire, Repair, Preserve: A Diagnosis-Guided Post-Training Recipe for Small-Model Dialogue Game Agents
Nan Li
Interactive dialogue games test a capability that static
benchmarks largely leave implicit: a model must carry state across turns, interpret feedback, and choose valid actions under changing constraints. We study this setting in the LM Playschool Challenge with a 2B open-weight model, and find that many failures are not only broad knowledge failures but also local decision failures: repeated guesses, malformed actions, and violations of feedback that the model has just seen. These diagnostics motivate a training recipe organized around three steps: acquire broad game participation through supervised fine-tuning, repair mechanically verifiable failures within one targeted dialogue-game family using turn-local preference pairs, and preserve general capabilities beyond these dialogue games. In the official final evaluation, our submission improves public clemscore from 10.67 to 38.92 and closed in-domain score from 13.41 to 41.17, while approximately preserving aggregate static performance (44.14 vs. 44.24 for the baseline). Out-of-domain clemscore remains low at 7.88, with the largest gains concentrated in unseen variants of the targeted family. Our results suggest that broad SFT brings most of the model's capability improvement; turn-local supervision can be effective when failure detection is precise, with observed transfer concentrated primarily within-family.
Read the full abstract ▾
Computer Vision
ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
Huseyin Umut Isik, Mehmet Alp Ozaydin, Sila Kurugol et al. (+1 more)
Contrastive
vision-
language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labels. However, two characteristics of chest CT challenge conventional global contrastive learning. First, many critical abnormalities are small or anatomically localized, and pooling an en- tire volume into a single
embedding may dilute their visual evidence. Second, the standard contrastive objective treats every other scan in a batch as a negative. Because many chest CTs share abnormalities, this objective incorrectly pushes co-positive pairs apart. We propose Anatomy-Routed Contrastive Learning for 3D Chest CT (ARC-CT), a region-aware framework that addresses these limitations using only la- bels extracted from reports by an LLM, with no manual annotations or bounding boxes. ARC-CT combines three components: (1) an Anato- myQFormer localizing evidence via queries constrained by automatically generated organ masks; (2) a label-Jaccard soft InfoNCE objective in- tegrating the standard one-hot target with the label-set overlap of each pair, which reduces false-negative penalties between studies that share clinical findings; and (3) an organ-level
alignment loss connecting mask- pooled visual features to organ-specific report text extracted offline with a large
language model. ARC-CT achieves a 0.86 mask-free macro AUC across 18 abnormalities using a compact 3D ResNet-18 backbone. Over- all, ARC-CT outperforms both comparable efficient baselines and sev- eral larger
transformer models. Our code and weights are available at https://github.com/arc-ct/arc-ct.
Read the full abstract ▾
All authors Huseyin Umut Isik, Mehmet Alp Ozaydin, Sila Kurugol, Şeyda Ertekin
Computer Vision
Prompt-Guided Interactive Segmentation of Interstitial Lung Disease in Thoracic CT
Vasilis Dedousis, Lubnaa Abdur Rahman, Lorenzo Brigat{\omicron} et al. (+8 more)
Accurate
segmentation of interstitial lung disease (ILD) patterns is essential for quantitative disease assessment and longitudinal monitoring. However, existing approaches remain limited by relying on dense annotations and producing static predictions that cannot be refined, motivating interactive approaches. While promptable models show promise in interactive
segmentation, their adaptation to ILDs remains largely unexplored. To address this gap, we investigate
prompt-guided foundation models for ILD refinement and present, to the best of our knowledge, the first adaptation of MedSAM2 for interactive 3D ILD
segmentation on thoracic CT. We investigate three fine-tuning strategies and multiple clinically motivated
prompts: bounding-boxes (BBox), point, lasso, and scribble. On a
dataset spanning seven ILD patterns and healthy lung tissue, full model fine-tuning performed best, improving the average Dice score by 4.7 percentage points over MedSAM2.While BBox
prompts achieve the strongest performance, non-native MedSAM2 interactions such as lasso and scribble
prompts also prove effective. Finally, we present and evaluate a proof-of-concept end-to-end workflow in which MedSAM2 is initialized from an automatic
segmentation prior and subsequently refined using radiologist
prompts. Model weights and plug-ins made available at: https://github.com/AIHNlab/ILD-SemiSegTool.
Read the full abstract ▾
All authors Vasilis Dedousis, Lubnaa Abdur Rahman, Lorenzo Brigat{\omicron}, Ethan Dack, Andreas Christe, Christoph Frank, Manuela Funke-Chambour, Justus Roos, Adrian Huber, Lukas Ebner, Stavroula Mougiakakou
Discrete Mathematics · Cross-listed from math.CO
An Exposition of the $\widetilde{O}(\log^{1/4} n)$ Bound for the Komlós Problem
Nikhil Bansal and Haotian Jiang
A
conjecture of Komlós states that the combinatorial discrepancy of any
matrix $A\in\mathbb R^{m\times n}$ whose columns have Euclidean norm at most one is bounded by a universal constant. We prove that the combinatorial discrepancy of every such
matrix is at most $O((\log n)^{1/4}(\log\log n)^{7/4})$. This is the first asymptotic improvement over the $O(\sqrt{\log n})$ bound established by Banaszczyk [Banaszczyk, Random Struct.\
Algorithms, 1998], and it refutes a
conjecture of Hajela [Hajela, European J.\ Combin., 1988] that a lower bound of order $\Omega(\sqrt{\log n})$ should hold.
Read the full abstract ▾
Artificial Intelligence
Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning
Minghui Xu and Zi Wang
Current large
language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical
reasoning on the Countdown task. We first analyze
reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning
datasets to teach the model useful tool-use patterns and how to interpret returned outputs. Building on this tool-formatted policy, we apply several on-policy reinforcement learning methods, including RLOO, RLOO++, GRPO, and DAPO, using automatically verifiable final-answer rewards. To enable a more reliable evaluation, we construct a fresh 1,024-problem held-out Countdown
benchmark with no exact overlap with the training data. Our results show that calculator tool integration consistently improves both SFT and RL baselines, yielding roughly 10 percentage-point gains across pass@k. Among the RL methods, Tool-DAPO achieves the strongest performance, improving pass@1 from 35.8% for Tool-SFT to 66.0%. Further analysis shows that RL encourages more effective tool use even when only final-answer rewards are provided. These findings suggest that tool integration reduces arithmetic and verification errors, while RL increases the probability of correct
reasoning traces.
Read the full abstract ▾
Machine Learning · Cross-listed from math.ST
Generalized Splines and Gaussian Processes
Michael Unser
For finite-dimensional linear inverse problems where the variables are Gaussian, it is well-known that the minimum-mean-square error
estimator takes the form of a regularized least-squares data fit. In this chapter, we show that this equivalence extends to a much broader infinite-dimensional setting where generalized splines take the role of linear regressors and generalized Gaussian processes on a
nuclear space $S$ are the counterpart of Gaussian random vectors. The scope of this extension is of the same nature as the switch from the classic notion of function to that of a distribution, also known as a "generalized function." Our formalism involves a whitening/regularization operator $L: S\to S'$ whose continuous extension induces a native
Hilbert space $H\subset S'$ that plays a central role in our characterization. The presentation is self-contained for the most part and remarkably general and powerful. It allows for the recovery of all known instances of such equivalences; in particular, the methods involving innovations and reproducing-kernel
Hilbert spaces developed by Kailath and his students, and the mathematical correspondence between fractional splines and Mandelbrot's fractional Brownian motion (fractals), with the former being the optimal
estimators of the latter. It also covers general
Bayesian methods for the resolution of infinite-dimensional inverse problems.
Read the full abstract ▾
Computation and Language
Sliding-window beats linear attention
Alexia Jolicoeur-Martineau, Rhea Sanjay Sukthanker, Pashmina Cameron et al. (+1 more)
Due to the nature of quadratic
attention, Large
Language Models (LLMs) consume a lot of
memory and energy: every new
token costs more than the previous one, and its keys and values must be stored in
memory indefinitely, which is unsustainable. Two main lines of work address this: compressing the KV cache, e.g., by evicting or quantizing keys and values, and retrofitting LLMs to use Linear
Attention, which replaces the KV cache with a fixed-size state. Retrofitting has attracted a lot of
attention, given its promise to solve the quadratic scaling problem with state-of-the-art performance at low cost. However, it has not been properly compared to the simplest form of KV-cache eviction: Sliding Window
Attention (SWA) with
attention sinks. In this work, we show that SWA with sinks performs as well or better than most retrofitted Linear
Attention models across multiple LLMs and downstream tasks, with the largest gains on long-context and generative tasks. On long-context
reasoning tasks (Needle-in-a-Haystack and BABILong), SWA achieves massively higher performance (2 to 10 times higher than linear
attention). SWA requires no additional training, is extremely fast, and requires little
memory, making it an extremely cheap and reliable solution. When the training budget is limited, switching to SWA is a much more effective way to reduce inference
memory cost than retrofitting linear
attention. Linear
attention models have shown promise, but they require training from scratch or extensive retrofitting to reap their architectural benefits and come close to SWA.
Read the full abstract ▾
All authors Alexia Jolicoeur-Martineau, Rhea Sanjay Sukthanker, Pashmina Cameron, Emy Gervais
Logic in Computer Science
Self-extensional logics of formal inconsistency: Decidability and limits for paraconsistency
Marcelo E. Coniglio and Héctor Federico Mallea
RmbC is a self-extensional paraconsistent logic in the family of Logics of Formal Inconsistency (LFIs). This system is obtained from mbC (the basic LFI) by adding the replacement property via two global inference rules. RmbC is characterized by a non-explosive negation $\neg$ and a consistency operator $\circ$, which recovers the principle of explosion in a controlled way. Together with its principal axiomatic extensions, RmbC admits a standard Lindenbaum-Tarski algebraization, with Boolean
algebras with LFI operators (BALFIs) as its algebraic semantics. In this paper, we study how far this self-extensional paraconsistent behavior can be extended axiomatically, starting from RmbC. We classify pairs of very natural consistency axioms according to whether they preserve paraconsistency or force classical collapse; identify six minimal explosive combinations that collapse to a single algebraic core; and isolate a separate structural obstruction for the combination of excluded middle for $\neg$ with an involutive negation. We also investigate, for the first time, the decidability of this family of self-extensional LFIs. As a first result, we prove the finite model property for RmbC with respect to BALFI semantics via an algebraic filtration, which yields decidability, and transfer this result to several paraconsistent axiomatic extensions of RmbC. Finally, we establish a coNEXPTIME upper bound for the validity problem of RmbC and a coNP-hardness lower bound, and prove coNP-completeness for the principal extensions containing one of the six minimal explosive pairs.
Read the full abstract ▾
Machine Learning
Curvature-Conditioned Multiscale Momentum with Sphere Constraints for LLM Pretraining
Shuchen Zhu, Yuxin Fang, Mingze Wang et al. (+1 more)
Pretraining accounts for a large fraction of the total computational cost in LLM training. However, noise-dominant gradients and the highly ill-conditioned loss landscape bring severe challenges. Although modern adaptive optimizers such as AdamW and
Muon have achieved great success in large-scale pretraining, their reliance on gradient normalization offers limited mitigation of the ill-conditioned
curvature. The progress along flat directions (eigen-directions of small
eigenvalues), which dominates the final loss reduction, remains relatively slow. To enhance training dynamics along flat directions, we propose a
curvature-conditioned multiscale momentum method with sphere constraints, delivering steady acceleration in LLM pretraining. This multiscale momentum, applied only along flat directions, pairs a slow-decay component for noise reduction with a fast-decay component for rapid
curvature adaptation, harnessing their complementary strengths. Crucially, we employ a sphere constraint technique to prevent parameter inflation and excessively rapid effective learning rate decay that would otherwise arise from a naive combination. Extensive experiments show that the proposed method significantly accelerates
Muon across diverse architectures (dense, MoE) and model sizes (0.12B–2.3B parameters). Theoretically, we verify the acceleration effect and provide insight into the design principles underlying the flat-direction multiscale momentum.
Read the full abstract ▾
All authors Shuchen Zhu, Yuxin Fang, Mingze Wang, Kun Yuan
Information Theory
Significance-Driven Semantic Communication
Christian McDowell, Andrea Panebianco, Sirin Chakraborty et al. (+1 more)
In this paper, we study a significance-driven cross- layer semantic communication design problem. Based on sta- tistical decision theory, we introduce an information-theoretic measure of per-sample data significance that quantifies the task-specific value of each individual observation. Using this metric, we formulate a cross-layer optimization problem that simultaneously optimizes (i) physical-layer semantic encoding and inference and (ii) MAC-layer resource allocation, with the objective of maximizing semantic spectrum efficiency, defined as the semantic value delivered per unit bandwidth per unit time. At the physical layer, we develop Meta-Learning Variational Information Bottleneck (Meta-VIB), a new semantic transceiver that employs a meta-learned hypernetwork to compress high- dimensional observations into semantically significant latents, enabling instantaneous adaptation to dynamic channel conditions and varying symbol budgets without online retraining. At the MAC layer, we model channel allocation as a Multi-Action Restless Multi-Armed Bandit (MA-RMAB) and adopt the Q- Maximization
algorithm, which dynamically allocates channel resources to sensors based on their semantic value of information. Experimental results on a real-world pedestrian safety
dataset demonstrate that our joint design achieves substantial gains in semantic spectrum efficiency over baselines, reaching up to 1000 times gain at an average SNR of 0 dB and 40 times gain at an average SNR of 5 dB.
Read the full abstract ▾
All authors Christian McDowell, Andrea Panebianco, Sirin Chakraborty, Yin Sun
Computation and Language
Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction
Qing Ye and Meng-Hsuan Lin
One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a structured-output constraint had silently disabled tool use, and the model answered anyway, with fabricated source text. Only the per-tool trace exposed it. Fidelity – whether an extracted value matches the source – is the standard measure for agentic document extraction, and it scores that run a success. We therefore log every tool call in an agentic
benchmark of 25 hand-curated claims over three components, with 12 more on a fourth, 37 in all. From that dispatch record we build two instruments: a rule-based failure-attribution classifier, and a silent-failure detector whose two rules check only which tools were called, never the extracted value. The detector raises no flag on 207 clean fidelity-passing extractions across three model families, and recovers all 50 planted faults that withhold exactly the tools its rules check. The two results are not symmetric: the first bounds the false-positive rate, the second is recall by construction, and detection power against runs that call their tools and still answer wrongly is unmeasured. A second, independent oracle, a causal chamber that tests whether the datasheet's claims hold under physical measurement, is intentionally partial: it confirms only what the apparatus can exercise, a verifiable envelope of 2 of those 37 claims, and we give a taxonomy of why the rest are not physically gradable. Under a controlled perturbation, fidelity passes throughout while the chamber verdict flips exactly at the measurement uncertainty. Across three deployed model stacks (one destabilised by its serving stack, not by any capability gap) the tool layer buys portability and observability rather than accuracy, and earns its premium only once a document outgrows the context window.
Read the full abstract ▾
Systems and Control
LUCID: An Agentic AI Framework on Digital-Twin in the Loop for QoS-Guaranteeing Robotic Control
Hyeonsu Lyu, Minwoo Kim, Sehyun Ryu et al. (+1 more)
Cloud robotics relies on the timely uplink of high-volume sensing streams, yet dynamic environments continually shift the feasible combinations of trajectories, active-
robot count, and per-
robot QoS. Because existing approaches formulate trajectory planning (TP) and
radio resource management (RRM) as a single fixed optimization problem, they cannot reconfigure these coupled decisions as conditions evolve, resulting in transient QoS violations. However, evolving operator intents change which quantities-such as the active-
robot count and per-
robot QoS-are fixed, optimized, or relaxed. Furthermore, the computational cost of evaluating trajectory-dependent wireless conflicts has made it difficult to build large-scale Digital-Twin-in-the-Loop (DITL) testbeds responsive enough for such dynamic orchestration. We present LUCID, an LLM-
agent–orchestrated, uplink-aware cloud-robotics pipeline that moves TP–RRM from solving a fixed formulation to dynamically orchestrating optimization problem schemas within a DITL environment. Driven by the operator's high-level intent, LUCID treats the TP–RRM formulation as a bounded template whose variables, objectives, and constraints are dynamically configured, while SimBridge enables repeated ray-tracing evaluation by converting large-scale robotics scenes into wireless-ready DTs. By integrating collision-free path planning with a spectral-radius RRM validator, LUCID identifies wireless bottlenecks and restructures the problem schema on the fly to efficiently find the verified feasible state. Experiments confirm that LUCID robustly adapts to changing intents, active-
robot counts, and scenes, while a
multimodal surrogate model, FastConfigNet, reduces planning latency.
Read the full abstract ▾
All authors Hyeonsu Lyu, Minwoo Kim, Sehyun Ryu, Hyun Jong Yang
Robotics
Linear Temporal Logic Translation via Human-Inspired Self-Constrained Reasoning for Robot Task Specification
Haofei Hou, Fanxu Meng, Shunyi Zhao et al. (+4 more)
Many robotic tasks are temporally extended and demand precise specifications of subgoals, constraints, and their temporal ordering. Yet human operators typically communicate such tasks in natural
language, which is inherently ambiguous, underspecified, and context dependent. Translating human instructions into formal task specifications, such as Linear Temporal Logic (LTL), is therefore essential for verifiable and safe robotic execution. Existing LLM-based translators attempt to bridge this gap through open-ended
reasoning or post-hoc constraint enforcement, but the former may violate domain constraints, whereas the latter can disrupt the
reasoning needed for novel instructions. This paper proposes Self-Constrained
Reasoning (SCR), a framework that mitigates this trade-off by internalizing structural knowledge into the model's decision-making process rather than imposing it as an external filter. By combining a structural constraint representation with a hierarchical decision-making formulation, SCR guides
reasoning within a formally grounded space while preserving adaptability to unseen instructions. Experiments show that SCR improves both domain-constraint satisfaction and generalization, providing an effective and interpretable approach for translating human intent into verifiable specifications for robotic execution.
Read the full abstract ▾
All authors Haofei Hou, Fanxu Meng, Shunyi Zhao, Kairui Yang, Mengchen Cai, Lecheng Ruan, Qining Wang
Artificial Intelligence
Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
Shuze Chen, Kunal Marwaha, Xiaoyang Lu et al. (+2 more)
Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barriers to entry, including the need for expertise in formal verification (as well as the underlying mathematics) and the significant time required for writing formal proofs. AI coding
agents have dramatically reduced these barriers; human users can now use natural
language to
prompt agents to write complex proofs in Lean. This opens up the intriguing possibility of internet-scale mathematical collaboration involving both humans and AI
agents, where correctness is machine-checked. To realize this possibility, we introduce Prove2Me (https://prove2.me), an open collaborative platform for formalizing mathematics. Users launch formalization "missions", to which AI
agents contribute formal proofs toward completion. We designed mechanisms and a specialized harness in Prove2Me that enable large-scale collaboration so that
agents can build on one another's work and freely reuse existing results. In doing so, Prove2Me aims to turn math formalization into a scalable, crowd-sourced effort open to anyone with an
agent.
Read the full abstract ▾
All authors Shuze Chen, Kunal Marwaha, Xiaoyang Lu, Henry Yuen, Tianyi Peng
Computation and Language
Are These Modules Worth Their Cost? A Paradigm-Level Accuracy-Cost Analysis of In-context Learning Text-to-SQL
Jiayan Lin, Yujia Liu, Zijin Hong et al. (+6 more)
Recent advances in in-context learning (ICL) text-to-SQL have substantially improved execution accuracy on public
benchmarks by assembling increasingly elaborate pipelines around the base generator, yet existing studies typically report aggregate end-to-end accuracy, without quantifying the marginal accuracy-cost contribution of individual design choices. Consequently, providing a unified, paradigm-level cost-accuracy quantification remains a critical challenge for understanding and configuring modern text-to-SQL. To address this, we instantiate 17 paradigm-level configurations across five recurring modules of the ICL text-to-SQL pipeline under a single controlled implementation, and attribute each paradigm's marginal contribution and incurred cost across all four backbones spanning diverse capability levels and
reasoning styles. Our analysis reveals that execution-feedback refinement is the only paradigm whose benefit holds universally at consistently low cost, while most other modules help only under backbone-dependent conditions.
Token accounting shows that input demand is more closely tied to pipeline structure, whereas output demand is more sensitive to backbone generation behavior. Cross-module analysis further shows that stacking improves accuracy on most backbones, although how the gains compose varies with backbone capability. We also find that a fixed budget is often better spent engineering a more elaborate pipeline over a mid-tier backbone than upgrading to a frontier model with a lean pipeline. These findings distill into an actionable, cost-aware tiered guideline that transfers to five additional backbones without per-paradigm search.
Read the full abstract ▾
All authors Jiayan Lin, Yujia Liu, Zijin Hong, Zheng Yuan, Yilin Xiao, Hao Chen, Qinggang Zhang, Xiao Huang, Feiran Huang
Computer Vision
Lossy Event Compression: From Event Stream Distortion to Task Performance
Zahra Rezaee, Catarina Brites and João Ascenso
Event cameras generate asynchronous, sparse data streams with microsecond temporal resolution, but in moderate-to-high motion scenes they can produce as many as hundreds of millions of events per second, creating significant bandwidth and storage challenges. Lossy compression is therefore essential for practical deployment, yet existing event stream distortion metrics fail to reliably predict compression-induced degradation at the task level, forcing codec optimization to rely on expensive task-specific evaluations. To address this gap, this paper introduces two fundamentally different event compression pipelines: i) an aggregation-based pipeline that converts the event stream into polarity-based histogram frames for compression with the conventional image codec JPEG 2000, and ii) a frame-free point cloud-based pipeline that codes events natively as 3D points using the octree-based codec G-PCC. Both pipelines are then assessed within a unified task-driven evaluation framework that relates event stream distortion to downstream application performance across four representative tasks: i)
video reconstruction, ii) object detection, iii) optical flow estimation, and a delay-sensitive task iv) asynchronous feature tracking under a reference-relative protocol. Building on this framework, five classification-based distortion metrics are applied to event compression for the first time, to the best of the authors' knowledge, and benchmarked against existing event stream metrics. Experimental results demonstrate that the proposed metrics reliably predict compression-induced task degradation across different coding frameworks. This demonstrates that event stream distortion assessment can be an efficient alternative to repeated task-specific evaluation, providing direct guidance for the development and optimization of future event data coding solutions.
Read the full abstract ▾
Machine Learning
Euclidean Fourier Neural Operators
Nathanael Bosch, Niklas Frederik Schmitz and Michael F. Herbst
Fourier neural operators (FNOs) provide an efficient framework for learning mappings between function spaces as they are, by construction, independent of the grid resolution at which they are trained and evaluated. However, FNOs are not independent of the periodic domain they are applied to: their discrete spectral weights are indexed by integer
Fourier mode numbers, which correspond to physical wavevectors. When applied to a different domain, the same trained weights act at different wavevectors, and the FNO silently represents a different operator. This makes FNOs unsuitable for tasks where transfer across domains is crucial. We propose Euclidean
Fourier neural operators~(EFNOs) as a domain-independent alternative to FNOs. By parameterizing the spectral kernel as a continuous function of the physical wavevector, the EFNO can learn operators that act consistently across periodic domains of varying shape and size. We evaluate the EFNO on a simple heat equation and on a practically relevant materials science task of learning exchange-correlation potentials across different
crystal structures, and demonstrate that the EFNO is able to generalize to unseen grid sizes and domains.
Read the full abstract ▾
Artificial Intelligence
Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs
Vishvesh Bhat
Post training a
language model to reason means updating its weights. Supervised finetuning and reinforcement learning both place the acquired capability inside the model where it cannot be inspected cannot be checked step by step and cannot be moved to another model. We argue that for tasks whose intermediate steps admit verification,
reasoning is better placed outside the base models weights as an explicit program composed from deterministic and neural primitives. We introduce PLVR (Program Learning with Verifiable Rewards): a post training method that learns such programs directly from input-output examples. Its mechanism is symbolic backpropagation: each program layer carries a typed ontology a loss is computed at the output against ground truth and required input ontologies are propagated backward by type inference over primitive signatures: an analogue of the chain rule in which credit assignment is a derivation rather than an estimate. Where RLVR verifies a terminal outcome, PLVRs reward is a per step contract verdict dense over program structure. On LiveCodeBench v6 and Tau2Bench, 30B base models with PLVR outperform RL at matched budget by 27.8 points on average and frontier models an order of magnitude larger by 13.6 points. A single primitive library serves two
benchmarks, so the marginal cost of a new task is 100 examples of program search and no new finetuning data. Replacing the loss guided search with uniform sampling over the same type admissible space at equal budget collapses the median program from 65.6 to 17.5, identifying the backward pass rather than the type system as the source of the advantage. We release the symbolic backpropagation library and a conformance checker so the method can be applied to primitive libraries other than our own.
Read the full abstract ▾
Human-Computer Interaction
Between Algorithm (AI) and Intuition (Human): Preserving Designer Agency in AI-Assisted Sensemaking of Qualitative UX Data
Md Haseen Akhtar
The integration of AI into qualitative design research presents a fundamental tension: how do we leverage AI while preserving the subjective, intuitive judgments that define design expertise? This paper examines this question through a case study of analyzing 20 user responses about
video conferencing platforms for educational contexts. We argue that AI sensemaking tools risk flattening the rich data patterns, amplifying contradictory textures of user feedback into sterile categories thereby transforming design research from an interpretive craft into a mechanical sorting exercise (rigid and formal). Through comparative analysis of AI-assisted sensemaking versus human-centered approaches to the same
dataset, we identify when algorithmic efficiency enhances understanding and when it diminishes the designer's interpretive agency (uncovering hidden needs, critical enquiry, what if enquiries, making decisions, having trade-offs). We present a framework for augmented sensemaking that positions AI as an instrument for amplifying human judgment rather than replacing it. Our findings suggest that the most valuable role for AI in design research is not to eliminate subjectivity, but to make it more intentional, reflective, and accountable.
Read the full abstract ▾
Cryptography and Security
Exploiting Per-Core Leakage: Electromagnetic Side-Channel Monitoring of Multicore Architectures
Daehyeon Bae, Sujin Park, Insup Lee et al. (+4 more)
Multicore processors are increasingly adopted in embedded systems to meet growing performance demands. However, physical side-channel analysis of multicore architectures remains underexplored, as obtaining usable leakage is inherently challenging. Consequently, side-channel security research on such systems has lagged far behind, leaving a critical security gap. To address this gap, we reveal the electromagnetic leakage mechanisms in multicore architectures and, for the first time, demonstrate per-core leakage exploitation, thereby enabling physical side-channel analysis for these systems. As a practical extension, we present a non-intrusive side-channel monitoring method that achieves per-core granularity. To validate its feasibility and practicality, we implement a prototype on a heterogeneous SoC platform with an RF front-end, and evaluate on a commercial off-the-shelf quad-core embedded system, the Raspberry Pi 4B with ARM Cortex-A72 cores.
Read the full abstract ▾
All authors Daehyeon Bae, Sujin Park, Insup Lee, YoungGiu Jung, Kyeongsik Lee, HeeSeok Kim, Seokhie Hong
Cryptography and Security
LongPIBench: A Long-Context Benchmark for Prompt Injection
Yupei Liu, Yuqi Jia, Neil Zhenqiang Gong et al. (+1 more)
Prompt injection attacks pose a serious security risk to large
language models in real-world applications. However, existing
prompt injection
benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a substantial overestimation of the effectiveness of current defenses. In this paper, we bridge the gap by introducing LongPIBench, a long-context
benchmark for
prompt injection covering 4 realistic application scenarios: paper peer review, resume screening, code review, and email summary. For each scenario, we construct a synthetic
dataset and a real-world
dataset, with context lengths ranging from thousands to tens of thousands of
tokens. The evaluation results on LongPIBench reveal significant vulnerabilities of
prompt injection defenses under long-context settings: even simple heuristic
prompt injection attacks achieve high success rates and frequently bypass state-of-the-art defenses. We hope LongPIBench can serve as a practical
benchmark for systematically evaluating
prompt injection defenses in realistic long-context scenarios.
Read the full abstract ▾
All authors Yupei Liu, Yuqi Jia, Neil Zhenqiang Gong, Jinyuan Jia
Robotics
Cooperative Risk-Aware Exploration in Heterogeneous Multi-Robot Systems Using Algorithmic Altruism
Brooks A. Butler, Jair Certório, João P. Hespanha et al. (+1 more)
Multi-
robot systems are well-positioned for exploration in hazardous environments, but effective deployment requires deciding not only where
robots should gather information, but also how risk should be distributed across heterogeneous team members. This paper develops a game-theoretic framework for cooperative risk-aware exploration based on ecologically inspired altruistic behavior. Each
robot selects a finite-horizon trajectory to maximize information gain while penalizing redundant exploration and expected hazard exposure. Heterogeneity is introduced through
agent-specific value parameters for encoding altruistic coupling, which is modeled through relatedness weights inspired by Hamilton's rule. We introduce a game-theoretic structure for trajectory planning that defines a Social Nash
Equilibrium, which modifies the utility of
agent actions according to
agent relatedness. This utility shaping causes
agents to internalize the effect of their trajectory choices on teammates, encouraging lower-valued
robots to accept risk when doing so benefits higher-valued
agents and improves team performance. We define an exploration utility for
agents that rewards area coverage and uncertainty reduction, while also penalizing redundancy and risk, enabling projected gradient-based waypoint optimization in a receding-horizon planner. Simulations show that altruistic planning reduces redundant exploration, improves inter-
robot separation, and reallocates risk according to
agent value while maintaining comparable map coverage. We further demonstrate the approach in hardware experiments, where planned waypoints are tracked by wheeled
robots using single-integrator controllers and barrier certificates.
Read the full abstract ▾
All authors Brooks A. Butler, Jair Certório, João P. Hespanha, Magnus Egerstedt
Machine Learning
SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data
Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou et al. (+2 more)
Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient feature informativeness. Automated Feature Engineering (AutoFE) overcomes this by automating feature generation and selection, ensuring both model performance and operational efficiency. However, traditional AutoFE often yield features with poor interpretability because they rely on blind mathematical transformations, while large
language models (LLM)-based AutoFE faces challenges in requiring costly multi-round iterations to generate high-utility features to effectively enhance model performance, compounded by inherent risks of bias and
hallucination. In this paper, we combine symbolic regression with LLMs for feature engineering (SymboLLM-FE) to solve these challenges. We extract mathematically expressive formulas strongly correlated with the target via symbolic regression, which can enhance model performance, then refine them by LLMs with rich prior knowledge to ensure interpretability. Empirical results on six real-world
datasets and four Kaggle competitions demonstrate that SymboLLM-FE outperforms existing AutoFE. SymboLLM-FE also addresses the dual challenges of poor interpretability and numerous iterations by employing a statistical prior-grounded LLM refinement mechanism and single-digit LLM calls.
Read the full abstract ▾
All authors Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo
Computation and Language
A Unified Framework to Elicit Structured Feedback for Interpretable Multi-Trait Essay Scoring
Shihang Yang, Sanwoo Lee, Ningning Zhao et al. (+1 more)
Multi-trait Automated Essay Scoring (AES) requires rubric-grounded
reasoning across interdependent traits, rather than isolated score prediction. Existing feedback-enhanced methods often decouple feedback from scoring or assess traits independently, weakening score–feedback consistency and rubric
alignment. We propose HiFTS, a unified autoregressive framework that generates hierarchical CoT feedback before predicting trait-level and holistic scores. HiFTS distills rubric-grounded hierarchical CoT feedback from a teacher LLM and trains student models to jointly generate feedback and scores. HiFTS further applies Group Relative Policy Optimization with a composite reward balancing score agreement, calibration, feedback quality, and structural validity. At inference, a lightweight global prior provides holistic guidance to reduce drift during long-form
reasoning. We also introduce CFMS-34, a Chinese multi-trait AES
dataset with 951 essays annotated with holistic scores and 34 rubric-based traits. Experiments on CFMS-34 and ASAP++ show that HiFTS achieves strong holistic and trait-level scoring while producing coherent, rubric-aligned feedback.
Read the full abstract ▾
All authors Shihang Yang, Sanwoo Lee, Ningning Zhao, Yunfang Wu
Computer Vision
Post-Training VLMs for Video Mistake Detection
Federico Spurio, Olga Zatsarynna, Lars Doorenbos et al. (+3 more)
Human mistakes are inevitable when following instructions, yet they can lead to severe consequences. As such, there has been an increased interest in developing methods for detecting mistakes in
videos, with current methods mostly focusing on closed-set protocols. While successful in controlled settings, the closed-set assumption limits their wider applicability, as any changes to the task require collecting new data and re-training models. Instead, we argue that mistake detection methods should learn the general concept of a mistake, rather than overfitting to step-specific details. To reflect this, we introduce the Mistake Detection
Video Question Answering (MD-VQA) protocol and accompanying
benchmark. MD-VQA tests whether methods can discern if a step was executed correctly with respect to its description, for both seen and unseen actions. To address this important challenge, we propose the first
video-
language-model post-training technique for mistake detection. Our method uses a tailored reward function to encourage the model to identify discrepancies between an instruction and the corresponding
video. Extensive evaluations demonstrate that this approach outperforms zero-shot, supervised fine-tuning, and post-training baselines. Notably, our method generalizes especially well to unseen procedures, for instance, with an improvement of up to 11.6% over the best-performing baseline on EP-VQA, paving the way toward general mistake detection. We release our code and
benchmark at https://github.com/FedeSpu/mstk.
Read the full abstract ▾
All authors Federico Spurio, Olga Zatsarynna, Lars Doorenbos, Emad Bahrami, Gianpiero Francesca, Juergen Gall
Computation and Language
CultureConverse: A Multilingual Multi-turn Simulation Harness for Culturally Grounded Assistance in East and Southeast Asia
Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan et al. (+30 more)
Current cultural evaluations for large
language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common use case: users seeking practical help over multiple turns in culturally grounded scenarios. We introduce CultureConverse, a scalable,
multilingual simulation and evaluation harness for culturally grounded assistant dialogue that covers 10 East and Southeast Asian regions, 58 subgroup identities, and 7 domains. Each simulated and evaluated episode produces a scored interaction where the assistant assists the user and infers cultural constraints from partial information. The resulting CultureConverse-DS
dataset contains 14,610
benchmark (evaluation) episodes and 274,295 oracle-guided (gold-mode) dialogues. In our
benchmark evaluation of 18 models, GPT-5 mini achieves the highest assistance quality. Human annotation experiments suggest that our evaluation framework is a sufficient proxy for human judgment. Performance gains from fine-tuning on 27,860 high-quality CultureConverse-DS samples improve in-domain assistance and transfer out-of-domain to cultural MCQ and safety classification
benchmarks. We release the harness, both splits, and judge
prompts to support interactive evaluation of cultural competency.
Read the full abstract ▾
All authors Bryan Chen Zhengyu Tan, Weihua Zheng, Thong T. Doan, Bich Ngoc Doan, Jia Wang Peh, Xiaoyuan Yi, Jing Yao, Xing Xie, Nancy F. Chen, Zhengyuan Liu, JinYeong Bak, Wafi Shamdi, Soo Kai Chie, Liew Yu Siong, Aina Azyyati Binti Mohamad Rezal, Lew Yan Yan Vanessa, Huadan Wu, Dylan Raharja, Nadya Yuki Wangsajaya, Akane Fukushige, Kazushi Kato, Koji Inoue, Tatsuya Kawahara, Jaehyung Seo, Dongjun Kim, Seungyoon Lee, Zi Haur Pang, Rui Yang Tan, Charibeth Ko Cheng, Maria Regina Justina Estuar, Jann Railey Montalan, Pham Minh Duc, Roy Ka-Wei Lee