Sound
SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification
Giries Abu Ayoub, Loay Mualem and Simon Korman
Fully few-shot class-incremental audio classification (FFCAC) requires recognizing new sound classes from only a handful of labeled examples per session, without forgetting previously learned classes and without any large base
dataset. Existing methods typically freeze a pre-trained audio–
language encoder and classify with point prototypes, but they suffer from significant performance degradation throughout the sessions due to generic feature representations. We propose SPECTRA, a framework built on a frozen encoder which adds three components. (i) a lightweight trainable adapter that calibrates the generic
embeddings to the task; (ii) subspace feature replay, an exemplar-free anti-forgetting scheme that replays old classes by sampling from the low-rank subspace of their stored features; and (iii) a transductive optimal-transport refinement of prototypes at test time. Our central finding is that the subspace structure of the replay diminishes forgetting and outperforms naive Gaussian replay of equal variance. On three FFCAC
benchmarks (NSynth-100, FSC-89, LS-100), SPECTRA improves average accuracy and reduces forgetting over current state-of-the-art methods, and our ablations statistically validate each component.
Read the full abstract ▾
Hardware Architecture
Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels
Amir Taherin, Sana Taghipour Anvari, Charles Amante et al. (+9 more)
Edge LLM deployment is shaped by more than model size and precision: inference backend, hardware platform,
memory traffic, and power management all affect latency and efficiency. We present Hydra, a common-schema, phase-aware workload characterization framework for LLM inference on edge SoCs. Hydra instruments HuggingFace
Transformers and llama.cpp with a shared per-
prompt timing schema and fuses those records with hardware telemetry, enabling a multi-dimensional characterization of performance, system-resource utilization, and efficiency across prefill and decode phases. Using Hydra, we evaluate three consecutive edge System-on-Chip (SoC) generations (AGX Xavier, AGX Orin, and AGX Thor), 13 instruction-tuned LLMs from seven families, five execution formats, and consider input/output-length sensitivity. The resulting artifact contains roughly 107K per-
prompt records and is publicly released with Hydra. Our analysis shows that aggregate latency alone hides key deployment effects: backend structure changes where latency is introduced, quantization reduces
memory traffic and energy but does not predict power monotonically, and SoC generation changes how utilization and efficiency should be interpreted. By connecting phase-level timing with system-resource utilization and efficiency metrics, Hydra enables reproducible, phase-aware characterization of edge LLM inference. Hydra's source code and the collected per-
prompt trace corpus are available open-source at: https://github.com/amirtaherin/hydra
Read the full abstract ▾
All authors Amir Taherin, Sana Taghipour Anvari, Charles Amante, Yixiao Chen, Ruben Noroian, Zlatan Feric, Nicolas Bohm Agostini, Pu Zhao, José Cano, Bin Ren, Yanzhi Wang, David Kaeli
Machine Learning · Cross-listed from stat.ML
Improved Analysis for Hessian-free High-resolution Monte Carlo Sampling
Wujun Lv, Xiaoyu Wang, Yingli Wang et al. (+1 more)
Hessian-free high-resolution (HFHR) dynamics augments underdamped Langevin dynamics (ULD) with reversible position
diffusion for sampling problems that arise in machine learning. We establish an explicit quantitative contraction rate for HFHR dynamics under a position Poincaré inequality, weighted Hessian and
Laplacian bounds, and a compact Sobolev
embedding, where the potential function is not necessarily convex. An adapted time-augmented Poincaré inequality yields an explicit rate that improves upon the contraction rate of the underdamped Langevin dynamics. We also give a weak-solution construction and a self-contained spectral proof of the divergence lemma underlying the argument. For HFHR Monte Carlo (HFHRMC)
algorithm, which is based on a discretization scheme of HFHR dynamics, we use a path-space Girsanov argument to obtain a non-asymptotic convergence bound and an explicit iteration complexity in total variation distance. The bounds hold for every $\alpha\geq0$ and $\gamma>0$ and remain regular at the ULD endpoint. Optimizing the iteration complexity bound yields a positive, accuracy-dependent position-
diffusion parameter at finite accuracy, while its leading high-accuracy order coincides with that of the optimized ULD endpoint. Our iteration complexity bound improves upon the existing work on HFHR
algorithms. Numerical experiments including
Bayesian learning problems on real data are provided to illustrate the effect of positive $\alpha$ and its benefit.
Read the full abstract ▾
All authors Wujun Lv, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu
Software Engineering
ARISMA: Guidelines for AI- and LLM-Assisted Systematic Reviews, Scoping Reviews, and Mapping Studies
Mahyar Tourchi Moghaddam and Mina Alipour
Systematic reviews, scoping reviews, mapping studies, and related evidence syntheses are increasingly difficult to conduct with fully manual workflows as search volumes, update cycles, and synthesis requirements continue to expand. At the same time, artificial intelligence, machine learning, and large
language models are rapidly entering review practice across query formulation, screening, extraction, categorization, appraisal support, and reporting. Yet the empirical evidence remains uneven, task-dependent, and insufficient to justify unconstrained automation. Existing standards such as PRISMA 2020, PRISMA-S, PRISMA-ScR, PRISMA-P, PRESS, and SWiM remain essential, but none provides an end-to-end operational standard for when AI use is methodologically appropriate, how it should be validated, which review decisions must remain human-led, and how AI involvement should be reported so that readers can audit it. This paper proposes ARISMA, an AI Reporting and Integration standard for Systematic Methods and Analysis. ARISMA treats AI as an inspected, benchmarked, logged, and reversible assistant rather than an autonomous reviewer. It is built around one governing principle: every consequential scientific decision must remain human-interpretable, human-auditable, and human-accountable. The paper contributes a lifecycle taxonomy, process guidance, stepwise recommendations across the review pipeline, a governance and provenance model, a tool-support framework, an AI-integrated reporting checklist, and a validation
matrix. It also addresses legal,
privacy, infrastructure, and sustainability considerations. The framework was iteratively refined through structured expert consultation. The result is a practical and auditable guideline for responsible AI-assisted evidence synthesis.
Read the full abstract ▾
Social and Information Networks
Tabular Foundation Models for Multi-View Information Cascade Popularity Prediction
Wenting Zhu, Chenghua Gong, Sanchuan Guo et al. (+3 more)
Predicting the future popularity of information cascades is essential for understanding information
diffusion on social media. Despite recent advances, existing methods face two key limitations: they focus primarily on the cascade view while overlooking other information views that drive user engagement, such as textual semantics, visual content, and tabular attributes; and they fail to capture high-order cross-view interactions. To address these issues, we propose TFM4POP, the first framework to introduce tabular foundation models (TFMs) into popularity prediction, leveraging their pre-trained tabular priors to unify the modeling of multiple heterogeneous information views. Specifically, TFM4POP adopts a dual-branch design: the static branch employs a TFM as the feature-encoding backbone that jointly reasons over all static views through in-context learning to produce the static cascade representation, while the dynamic branch captures the continuous-time cascade dynamics with a dedicated Neural-ODE-based encoder. The two representations are then fused via cross-
attention for the final prediction. Furthermore, to adapt the TFM to real cascade distributions, we apply parameter-efficient IA3 fine-tuning, achieving performance competitive with or better than full fine-tuning while updating substantially fewer parameters. In addition, we construct a comprehensive multi-view cascade
benchmark that covers all four information views. Extensive experiments show that TFM4POP consistently outperforms state-of-the-art baselines across multiple
datasets and observation settings.
Read the full abstract ▾
All authors Wenting Zhu, Chenghua Gong, Sanchuan Guo, Chaozhuo Li, Yueyue Zhang, Xi Zhang
Numerical Analysis · Cross-listed from physics.comp-ph
Rapidly Convergent Finite-Element Domain Decomposition Method With Two-Channel Transmission Conditions
Furkan Ş{\i}k, Fernando L. Teixeira and Balasubramaniam Shanker
A novel dual-primal finite element tearing and interconnecting (FETI-DP) domain decomposition method (DDM) is introduced for solving Maxwell's equations. The proposed method is built upon a two-channel transmission condition (TC) enforcing both tangential-field and normal-flux continuity across subdomain interfaces. Two interface channels are separately constructed from the Faraday and Ampere-Maxwell equations. Simultaneously enforcing tangential-field and normal-flux continuity reduces interface jumps by several orders of magnitude relative to the widely used Robin TC. The resulting global interface equation exhibits markedly improved iterative convergence. Numerical experiments across different partitioning strategies, subdomain counts and volumes, mesh resolutions, and geometries demonstrate drastic reductions in iteration counts, while accuracy, massive parallelism, and scalability are preserved.
Read the full abstract ▾
Artificial Intelligence
LifePlanner: Evaluating LLM Agents for Geo-spatial Planning with Social Media Data
Zhen Dong, Yuning Peng, Yutao Shi et al. (+4 more)
Geo-spatial planning, like trip design, is a realistic testbed for LLM
agents because it requires grounded tool use, noisy evidence
retrieval, and multi-constraint
reasoning. Most
benchmarks, however, only provide clean geospatial data and tools, missing the open-ended social signals that people use in daily planning. We introduce LifePlanner, a
benchmark that enriches map data with large-scale local social media posts and provides access through an MCP toolset. LifePlanner provides an evaluation suite spanning four task categories and three difficulty levels. Experiments show frontier LLMs perform well on simple
retrieval but degrade sharply on complex planning, with the Pass Rate dropping to 40.2%. Results show that failures mainly stem from incomplete evidence acquisition from such a large
multimodal database, imprecise tool use, and weak constraint integration rather than model size or
reasoning length, suggesting that future progress requires effective grounded planning instead of scaling alone.
Read the full abstract ▾
All authors Zhen Dong, Yuning Peng, Yutao Shi, Lei Zhong, Yongsen Mao, Yuan Liu, Haiping Wang
Computation and Language
Padamitra: Grounded Glossary Generation for Classical Sanskrit
Manoj Balaji Jagadeeshan, Sai Pragnaan Marala and Pawan Goyal
We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translation-grounded meanings from a sloka-translation pair, formalizing the traditional patha commentary practice as an evaluable NLP objective. We construct a
benchmark of 31,316 sloka-translation-glossary triples from the Valmiki Ramayana and Srimad Bhagavatam, paired with two metrics: Jaccard for phrase recovery and Meaning Faithfulness for semantic consistency. Across zero-shot, few-shot, and instruction fine-tuned variants of Gemma-3n-E4B, Gemma-3-12B, Phi-4, and Qwen3.5-9B, instruction fine-tuning substantially outperforms prompting, while explicit
segmentation yields gains. Error analysis identifies over-
segmentation of sandhi and samasa compounds as the dominant failure mode, pointing to morphological modeling as the key bottleneck for faithful Sanskrit lexical decomposition.
Read the full abstract ▾
Artificial Intelligence
Retrieve, Match, Escalate: Accurate and Scalable Product Linking with VLM-Distilled Cross-Encoders and Agentic VLMs
Jian Wang, Steven Xu, Sanjyot Thete et al. (+5 more)
Product linking, the entity-resolution task of mapping merchant product records to canonical catalog products, consolidates fragmented listings so downstream search, recommendation, and advertising see one clean entry per product. At marketplace scale, billions of noisy, multi-category records must be resolved against tens of millions of canonical products, where scoring every candidate with a single model is either too weak for the hard cases or too costly for the easy ones. We present a production retrieve-then-match cascade that spends computation in proportion to difficulty:
retrieval surfaces plausible matches, a lightweight text cross-encoder auto-resolves the high-confidence majority, and an agentic
multimodal vision-
language model settles the ambiguous remainder by inspecting product images and issuing web searches for evidence that is in neither record. The cross-encoder is distilled from millions of dual-VLM-consensus labels, retiring human annotation from the training set, and is calibrated to auto-accept links at a 98% precision bar validated against a smaller operator-certified audit. The
agent is a self-hosted open-weight model that reaches a closed frontier VLM's precision at a four-point recall cost (88% versus 92%) for roughly one-seventh the per-pair cost, with no fine-tuning. Per-pair cost spans nearly five orders of magnitude from the cheap cross-encoder to the frontier VLM, so escalating only the hard tail to the
agent raises end-to-end link coverage from the cheap stage's 68% to 77%.
Read the full abstract ▾
All authors Jian Wang, Steven Xu, Sanjyot Thete, Maryam Barouti, Tom Tang, Elaine Wu, Charu Sareen, Kyle MacDonald
Machine Learning
On the Representational Geometry of Dynamic Programs
Richard F. M. Lim and Ruriko Yoshida
Standard neural architectures often fail to generalize to longer inputs for dynamic programming (DP) targets. We investigate what makes this hard geometrically. Every finite min-plus DP is a shortest path on a DAG, which is equivalently a tropical
polynomial whose extended Newton polyhedron encodes the decision boundary of which path wins. We prove these three descriptions (graph,
polynomial, polyhedron) form isomorphic semirings at two levels — formal
polynomials and their computed functions — connected by operations that characterize all structural redundancies. We then address the length-generalization question geometrically: does the decision boundary at length $T$ decide the boundary at $T+1$? We present two structural negatives. The semiring's two native ways to reduce dimension (setting a variable to each identity) are neither injective nor always closed within the DP. Series and parallel composition fail to construct all DAG
topologies from smaller sub-DAGs, and even all terminal-only operations do not capture all DP compositions.
Read the full abstract ▾
Data Structures and Algorithms
Fuzzy Pattern Matching in Ordered Structures
Armen Kostanyan and Arevik Harmandayan
The problem of pattern matching, that is, finding all occurrences of a given pattern in a string, is one of the fundamental problems in computer science that has applications in many areas. In this paper, we consider fuzzy patterns, defined as sequences of fuzzy properties over the basic alphabet. We first consider fuzzy pattern matching for sequences of elements of the basic alphabet and then extend the problem to partially ordered sets of nodes labeled by elements of the basic alphabet. For sequences, we seek segments that match the pattern, whereas for partially ordered structures, we seek saturated chains of nodes that match the pattern. The key concept underlying the solutions to these problems is the notion of a trajectory, which generalizes the concept of the prefix function used in the Knuth–Morris–Pratt (KMP)
algorithm. A trajectory is processed together with the corresponding data structure, allowing the proposed
algorithms to be represented as transition systems whose states are trajectories for sequences and trajectories associated with nodes for partially ordered structures. The trajectory-based approach provides a unified framework for fuzzy pattern matching in various data structures.
Read the full abstract ▾
Neural and Evolutionary Computing · Cross-listed from cond-mat.stat-mech
Directed walks shape a universal square-root law of entropy production rate in nonreciprocal systems
Thiparat Chotibut, Ewa Gudowska-Nowak and Maciej A. Nowak
The
entropy production rate (EPR) quantifies irreversibility of a nonequilibrium steady state, yet standard formulas obscure how a complex interaction network generates it. For multivariate Ornstein-Uhlenbeck dynamics on such networks, we express the EPR as a quadratic form in antisymmetric
matrices measuring the nonreciprocity of aggregate directed walks at every length, and, equivalently, as two weighted-walk quantities: pairs of directed walks sharing both endpoints, and directed closed walks. For diagonalizable interactions, an exact correspondence translates these walk quantities into
eigenvalues and biorthogonal eigenvector overlaps. Across dense, sparse, and deep acyclic random interactions satisfying matched-walk conditions, the mean EPR per node universally follows the square-root law $\phi_*(g)=1-\sqrt{1-g^2}$, where $g \in [0,1)$ parametrizes the interaction strength. Deep acyclic interaction
matrices are nilpotent, with all
eigenvalues fixed at zero for every $g$, yet, as their depth increases, their mean EPR per node approaches $\phi_*(g)$. Thus, the square-root law arises from directed walk properties, rather than from a shared spectral density or specific network
topology.
Read the full abstract ▾
Computation and Language
Behind the [MASK]: Disentangling Representation and Faithfulness in DAPF-Based Dementia Detection
Pardis Ranjbar-Noiey and Natalie Parde
Spoken-
language analysis via
prompt-based domain-adaptive models is a promising direction for low-resource, non-invasive dementia screening, but such models remain internally opaque. We study the interpretability of the Domain-Adapted models via
Prompt-based Fine-tuning (DAPF) framework, which casts dementia detection as diagnosis-related masked-
token prediction. We interpret DAPF and strong baselines using a variety of probing and analysis techniques, finding that DAPF achieved the best overall performance (accuracy=0.83 and macro-F1=0.83) with diagnosis most recoverable from its [MASK] representation. However, this representational advantage did not extend to
token-level explanation faithfulness. DAPF attributions primarily reflected
language task vocabulary, discourse markers, and transcription artifacts, with perturbation tests showing weak or negative effects. This suggests that its masked-
token interface determines diagnosis information without producing faithful
token-level explanations.
Read the full abstract ▾
Artificial Intelligence
CVE-SAI: Counterfactual Visual Evidence-Guided Selective Attribute Indexing for Risk-Controlled E-commerce Search
Xiaolong Sun, Qichao Wang, Hangyu Li et al. (+1 more)
Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying visual support, conflate transient prediction with persistent index admission, and lack explicit risk control over factually incorrect or visually unsupported values. We address these gaps with Counterfactual Visual Evidence-Guided Selective Attribute Indexing (CVE-SAI), which first infers and freezes an ontology-constrained candidate from the primary image and attribute question without catalog text, and then decides whether that candidate should enter the index. Focus-Zone Distortion (FZD) constructs an attribute-specific visual-dependence proxy through a controlled counterfactual intervention, and Evidence-Guided
Attention Redistribution (EGAR) uses the proxy to refine ontology-constrained scoring. The canonical candidate is frozen before evidence necessity, evidence retention, nuisance-transformation stability, and candidate-specific catalog-text conflict audits; catalog text can only tighten admission and cannot revise the candidate. Independent family-level calibration selects one policy with a simultaneous one-sided finite-sample bound under a 5% unsafe-admission budget. Experiments on five visual attributes derived from Amazon Berkeley Objects show that CVE-SAI improves attribute inference and evidence localization, achieves the highest certified admission coverage under the shared risk protocol, and yields the strongest controlled
retrieval performance with the lowest unsafe auto-induced exposure among automatic-admission systems. Separating inference from admission therefore enables visually supported attribute completion to improve
retrieval while limiting persistent index contamination.
Read the full abstract ▾
All authors Xiaolong Sun, Qichao Wang, Hangyu Li, Liang Chen
Computation and Language
A Primer on Computational Semantics for Artificial Intelligence Systems
Casey Kennington
As people adopt
transformer-based
language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such models learn and represent the meaning of the
language, and to be more informed about what
language is. This document is an attempt to help the reader understand how linguistic meaning (i.e., semantics) is approached from different fields of scientific and philosophical examination. I also explain three primary semantic theories: formal semantics, grounded semantics, and distributional semantics then compare how
transformer-based
language models differ from how humans learn
language.
Read the full abstract ▾
Machine Learning · Cross-listed from astro-ph.SR
EncoTESS: Age-Sensitive Encodings from Raw TESS Light Curves
Phil R. Van-Lane, Joshua S. Speagle, Ryan Cloutier et al. (+3 more)
Main sequence
stars of spectral types late F through M exhibit systematic variability in photometric light curves, particularly when they are young. Rotational modulation of starspots manifests as quasi-sinusoidal variability, which enables the measurement of rotation periods. Variability can also be
stochastic, as in
stellar flaring. However, since measurements of
stochastic processes depend on the time of observation, they are typically noisier. Considering that different manifestations of variability have unique observational nuances, models that naturally unify these are incredibly useful for
stellar characterization. Towards this goal, we have developed EncoTESS: a Time Series Foundation Model (TSFM) trained on a subset of TESS 2-min light curves. EncoTESS is specifically designed to handle the observational noise, heteroskedastic measurements, irregular sampling, and large data gaps common to TESS data. It is also ~1% of the size of a typical literature TSFM, so can be run easily on a modern laptop. EncoTESS encodes light curves into a fixed-size latent parameter space, which can be used to infer physical
stellar properties and recovers light curve summary statistics well. EncoTESS outperforms rotation period and variability amplitude as age indicators for
stars that have not converged onto the slow rotator sequence yet; broadly these include K and M
stars less than ~100 Myr, and M
stars less than ~1 Gyr. We focus on age inference as an application of EncoTESS in this work, but other downstream tasks such as
stellar classification could also be explored. The architecture of EncoTESS enables its future extension to TESS light curves of all cadences, and additional surveys such as Kepler and the upcoming PLATO mission. The core EncoTESS framework and library of encodings produced for the
stars used in this work are publicly available at https://github.com/philvanlane/encotess.
Read the full abstract ▾
All authors Phil R. Van-Lane, Joshua S. Speagle, Ryan Cloutier, Christopher A. Theissen, Gwendolyn M. Eadie, Ilay Kamai
Machine Learning
Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Models
Rishi Shah and Rishav Shrestha
A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exactly as evaluation will, decodes every rollout latent, and penalizes reconstruction error against ground truth. The term adds no parameters, costs training-time compute only, and reduces to the standard objective at weight zero, so every comparison in this paper is a one-flag A/B. On the chaotic Kuramoto-Sivashinsky equation, RDR raises valid prediction time (the time to first crossing of normalized error 0.5) from $3.87 \pm 0.23$ to $6.97 \pm 0.42$ time units at an identical 193,568 parameters, a $1.80\times$ improvement confirmed on seeds never used in selection and holding in 10 of 10 preregistered configurations at ratios of 1.71-2.50$\times$. The results come from a single system; a sweep in which the advantage grows with latent width is descriptive, and control experiments on two classic tasks are preliminary.
Read the full abstract ▾
Computation and Language
The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure
Kaiqiao Han, Katarzyna Pruś, Mark Steedman et al. (+1 more)
Recent work uses an NLI
benchmark of the imperfective paradox to argue that large
language models exhibit a Teleological Bias and Calibration Crisis. We identify three validity concerns in
benchmark construction, including aspectual reduction, semantic bias, and relation bias. Under a strict NLI standard, 76% of the Group A instances do not explicitly rule out culmination; in native-speaker annotation, 38% of Group A and 29% of Group C examples permit an alternative interpretation. To better isolate the semantic contrast, we construct Lexically Matched Minimal Pairs. Moreover, by formulating event-semantic NLI as a multi-step
reasoning problem, we evaluate intermediate semantic judgments and use oracle-guided settings. We find that incorrect NLI entailment does not fully support teleological bias. Prompting often changes final NLI decisions without reliably improving the underlying semantic judgments, offering a possible explanation for the Calibration Crisis.
Read the full abstract ▾
All authors Kaiqiao Han, Katarzyna Pruś, Mark Steedman, Yizhou Sun
Computation and Language
Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Philipp E. Glass, Allan Tucker, Yongmin Li et al. (+1 more)
Activation steering can be embedded directly into a
language model's weights, shaping behaviour without inference-time intervention and offering a way to encode
alignment prior to release. However, models are routinely fine-tuned after deployment, and it is unknown whether embedded interventions survive this. We study the stability of embedded steering for refusal ablation and brevity amplification across five instruction-tuned models (3B-14B) under non-
adversarial SFT and RLHF. We find that steering degrades more under stronger optimisation pressure against the steered behaviour, which depends on both the training data and the training
algorithm. Refusal ablation loses 69% of its effect on average under our SFT setup, but only 2% under our RLHF setup. The weight-edit, by contrast, remains almost unchanged (on average only 0.4% of it is restored), and the fine-tuning update along the steering direction is close to orthogonal to the pre-edit weight pattern (mean cosine similarity 0.071). Fine-tuning that restores the behaviour does so without reversing the edit. As the steered behaviour is not fully durable, embedded steering should be re-validated after downstream training.
Read the full abstract ▾
All authors Philipp E. Glass, Allan Tucker, Yongmin Li, Alina Miron
Machine Learning
D$^3$-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
Zechen Sun, Zhiwei Zhang, Fei Zhao et al. (+7 more)
Multi-teacher on-policy
distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix the per-domain data mixture before training, overlooking the fact that different domains converge at substantially different rates: some plateau early while others continue to improve throughout the training budget. A fixed mixture therefore wastes compute on fast-converging domains and undertrains slower-converging ones. To address this, we propose D$^3$-MOPD (Dynamic Domain ScheDuling for MOPD), a zero-overhead scheduler that repurposes the per-domain reverse-KL signal already produced during training to adapt the domain mixture online. Running asynchronously outside the training process, an off-process watcher periodically tracks each domain's KL trajectory, estimates remaining headroom and current improvement rate, and accordingly adjusts the domain sampling ratios without altering the core training loop. Our D$^3$-MOPD scales naturally to arbitrary numbers of domains, and the expected benefit grows as more domains introduce more diverse convergence patterns for the scheduler to exploit. On a Qwen3.6-35B-A3B student distilled from four domain-expert teachers, D$^3$-MOPD closes 97% of the average student-to-teacher performance gap, compared with 63% for vanilla MOPD, reaches the same peak performance with an approximately 3$\times$ reduction in rollout steps, and surpasses the specialist teachers on three of seven
benchmarks.
Read the full abstract ▾
All authors Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li, Mu Chuan, Huayu Deng, Guojian Zhan, Wenliang Chen, Yao Hu, Min Zhang
Artificial Intelligence
Solving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games
Durgam Latha, Dion Reji, S. Akshay et al. (+2 more)
Robust POMDPs (RPOMDPs) generalize classical POMDPs to the setting where exact transition probabilities are not known – rather, they are only known to belong to some uncertainty set of values. In this work, we study the problem of solving RPOMDPs with general omega-regular objectives, which subsume a broad class of objectives such as reachability, safety, and linear temporal logic (LTL) objectives. We show that, for (s,a)-rectangular RPOMDPs with polytopic uncertainty sets, the problem of solving RPOMDPs under omega-regular objectives can be reduced to solving partially observable
stochastic games (POSGs) under omega-regular objectives. Moreover, we show for the first time that reductions can be constructed in both directions, establishing the semantic equivalence between (s,a)-rectangular RPOMDPs with polytopic uncertainty sets and POSGs. This allows us to derive a range of new computational complexity results, including both upper and lower complexity bounds, on solving RPOMDPs with different omega-regular objectives. As a corollary, we also derive new computational complexity results for RMDPs.
Read the full abstract ▾
All authors Durgam Latha, Dion Reji, S. Akshay, {\DJ}or{\dj}e Žikelić, Shankaranarayanan Krishna
Numerical Analysis
A Symmetry-Preserving Tensor $\star_{\mathbf{M}}$-SVD
Victor Arsenescu and Misha E. Kilmer
Multiway data such as image collections and
video is ubiquitous, but the usual approach of flattening them into
matrices discards the cross-mode structure that often carries the signal. The t-product and its generalization, the $\star_{\mathbf{M}}$-product, give a
matrix-mimetic tensor
algebra with a tensor SVD whose truncation is optimal in the Frobenius norm, just as in the
matrix case. Much real data also has internal reflective
symmetry: frontal faces, manufactured parts, and leaves are all bilaterally symmetric. We define a
symmetry-preserving $\star_{\mathbf{M}}$-SVD that extends the
matrix symmetry-preserving SVD of Shah and Sorensen to the $\star_{\mathbf{M}}$-
algebra. When a tensor's transform-domain frontal slices are reflectively symmetric, the left basis of its $\star_{\mathbf{M}}$-SVD is symmetric too, so only its top half must be stored. Bilaterally symmetric images, turned on their side and stored as lateral slices, give such a tensor. This construction keeps the symmetric part of each image and stores only half the basis. We then recognize new images by projecting them onto this basis and matching to the nearest training image in coefficient space. Across ten
datasets of faces, leaves, butterfly wings, and other objects, the symmetric basis matches the recognition rate of ordinary tensor SVD at 2-11x less basis storage, with the exception of MUCT. On faces under varying illumination it exceeds the best rate the ordinary tensor SVD attains at any storage level.
Read the full abstract ▾
Computation and Language
Unsupervised Post-Training of Foundation Models: A Survey
Yijie Xu, Qianyi Cai, Huizai Yao et al. (+9 more)
Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning signal is derived from same-lineage model artifacts rather than an external oracle. We catalog 80 strict UPT methods and organize them by the object that supplies the update signal: a prediction statistic, a sample relation, a self-generated target, or an internal evaluator. Beyond inventory, we show how the choice of internal signal and task structure determines whether post-training improves the model or recursively amplifies error. An orthogonal Input Visibility $\times$ Update Persistence view maps deployment regimes and defines a unified framework for UPT selection and evaluation.
Read the full abstract ▾
All authors Yijie Xu, Qianyi Cai, Huizai Yao, Yili Wang, Tianfu Wang, Cehao Yang, Xingbo Yao, Zhiyu Guo, Aiwei Liu, Xuming Hu, Weiyu Guo, Hui Xiong
Artificial Intelligence
FrontierChallenge: Evaluating Scientific Workflow Completion
Liangcai Su, Zhaopeng Feng, Zhuo Chen et al. (+14 more)
Scientific
agents increasingly analyze data, execute code, and produce research artifacts, yet most
benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain
benchmark comprising 300 end-to-end scientific workflows. In this paper, we release and evaluate 97 of these tasks, spanning
quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment. Each task provides fixed inputs and specifies a bundle of required scientific deliverables. We evaluate twelve frontier models with three
agent scaffolds. Pass Rate measures the fraction of tasks satisfying the full-completion criterion, while Avg. Score captures partial progress. Each of the best-performing configurations completed only 20 of the 97 released tasks, yielding a Pass Rate of 20.6%. Partial progress translated especially poorly into complete delivery in analytical chemistry and electrochemistry/environment: Avg. Scores reached 87.6 and 94.9, but the highest Pass Rates were only 4% and 0%. Among non-passing Claude Code trajectories, 75.5% still ended with
language claiming completion. Complementary HDS6 process scores correlate strongly with task outcomes, supporting FrontierChallenge as a
benchmark of Heavy Duty Solver capabilities. These findings show that neither high partial scores nor confident claims of completion reliably indicate that a scientific task has been fully delivered, highlighting the need to evaluate end-to-end workflow execution and the completeness of scientific deliverables together.
Read the full abstract ▾
All authors Liangcai Su, Zhaopeng Feng, Zhuo Chen, Zhen Zhang, Xiang Lin, Ruilin Li, Handuo Zhang, Ning Wang, Kailong Wen, Yueqi Guo, Feng Xing, Yiling Guo, Brian Wang, Chenxiong Qian, Simon Shaolei Du, Lidong Bing, Xinyu Wang
Machine Learning
MSR-IVA: Masked Structural Residual Independent Vector Analysis for State-Aware Fusion of Structural MRI and Dynamic Functional Network Connectivity
Victor Solomon, Zening Fu, Rafal Angryk et al. (+2 more)
Multimodal fusion of structural MRI (sMRI) and dynamic functional network connectivity (dFNC) can reveal how
brain structure relates to changing functional states. When the same structural latent representation is coupled with multiple states, applying independent vector analysis (IVA) separately to each state can produce unrelated structural decompositions, while forcing identical decompositions may suppress state-specific relationships. In addition, not every subject expresses every dynamic state. We propose masked structural residual IVA (MSR-IVA), a state-aware framework that combines a shared structural representation with state-specific residual adaptations and masks for incomplete state expression. On an Alzheimer's Disease Neuroimaging Initiative cohort, MSR-IVA improved matched source coupling by 6.5% and reduced unmatched dependence by 15.7% relative to the independent pairwise IVA baseline. Among subjects expressing both states, mean absolute cross-state structural source correlation was 0.9177 for MSR-IVA versus 0.2978 for no sharing, demonstrating controlled structural sharing that preserves source correspondence while allowing state-specific adaptation.
Read the full abstract ▾
All authors Victor Solomon, Zening Fu, Rafal Angryk, Vince D. Calhoun, Jingyu Liu
Cryptography and Security
Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
Minh Tran, Cuong Dang, Tuc Nguyen et al. (+10 more)
Retrieval-Augmented Generation (RAG) enhances large
language models by grounding outputs in external knowledge, improving factuality and reducing
hallucinations. At the same time, the
retrieval-augmented pipeline introduces new robustness and security risks, including corpus poisoning,
backdoor attacks,
privacy leakage, and
fairness violations. Despite rapid progress in this area, existing surveys remain limited in their treatment of attacker objectives, threat models, and stage-specific defenses across the full RAG pipeline. This survey presents a unified and pipeline-aware overview of RAG robustness. We formalize threat models over the corpus, retriever, and generator, and organize attacks into three main objectives: accuracy,
privacy, and
fairness. We further review defenses from a pipeline-aware perspective, covering the
retrieval, rerank, generation, and traceback stages. In addition, we summarize robustness
benchmarks and explainability methods for more deeply evaluating and explaining RAG robustness.
Read the full abstract ▾
All authors Minh Tran, Cuong Dang, Tuc Nguyen, Khanh-Tung Tran, Minh Huynh Nguyen, Trinh Chau, Kien Le, Do Xuan Long, Jiahao Zhang, Fali Wang, Hoang D. Nguyen, Thanh Le, Suhang Wang
Digital Libraries
A Comparative Evaluation of Digitization Pipelines for Historiographical Sources
Marina Gómez Rey, Patricia Callejo, Mario Muñoz-Organero et al. (+1 more)
Purpose: The digitization of historical documents presents fundamental challenges for modern information
retrieval and Artificial Intelligence (AI) systems. Optical character recognition (OCR) errors in source corpora propagate through
retrieval-augmented generation (RAG) pipelines, compromising the factual accuracy of generated outputs. Methods: This study presents a systematic evaluation of PDF-to-text extraction pipelines applied to historiographical secondary sources on the Visigothic period. We assess thirteen distinct approaches spanning three methodological families: direct extraction, Large
Language Model (LLM) post-correction, and chunk-and-extract. Documents are stratified into five categories based on production method and visual complexity. Performance is measured using character error rate (CER) and word error rate (WER) against manually corrected ground truth. Results: Results demonstrate that direct extraction with Marker achieves superior performance (98.70% CER accuracy; 97.71% WER accuracy overall), while conventional OCR pipelines exhibit substantial degradation on scanned documents and complex layouts. Embedded-text extraction performs well on digital PDFs but fails on scanned documents. LLM post-correction does not provide systematic improvements and frequently degrades accurate extractions. Conclusion: End-to-end document parsing is the most reliable approach for heterogeneous historical collections. Document characteristics such as scan quality, layout complexity, and the presence of embedded text layers have a significant impact on extraction accuracy. LLM-based post-correction should not be assumed beneficial by default and requires validation before large-scale application.
Read the full abstract ▾
All authors Marina Gómez Rey, Patricia Callejo, Mario Muñoz-Organero, Carlos Alario-Hoyos
Machine Learning
Clearing the Underbrush: AI-Enhanced RF Interference Suppression
Rahul Jain, Pierre Trepagnier, Rick Gentile et al. (+2 more)
AI-based structured interference rejection has grown more popular because deep learning approaches can outperform traditional methods by jointly considering the signal of interest (SOI) and the signal mixture (SOI plus interference). This work builds on a previous AI-enabled approach utilizing autoregressive
transformer-based models by adding a Finite Scalar Quantization (FSQ) tokenizer layer which aims to improve the interference rejection performance while keeping overall latency to a minimum. Additionally, we experiment with other inference optimization techniques with the goal of speeding up inference without much accuracy loss. We explore this space with an experiment where the SOI is a digitally modulated
radio frequency (RF) signal and the structured interference is a digital television signal, an extremely common type of Orthogonal Frequency-Division Multiplexing (OFDM) transmission. Our results achieve low latency and increased interference rejection over traditional techniques and prior work with other AI-enabled methods. We demonstrate the benefits of the AI-enabled approaches via audio metrics such as Perceptual Evaluation of
Speech Quality (PESQ). Additionally, we explore a variety of applications and detail how our interference rejection
algorithm may be used in operationally-relevant scenarios.
Read the full abstract ▾
All authors Rahul Jain, Pierre Trepagnier, Rick Gentile, Joey Botero, Alexia Schulz
Machine Learning
Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation
Peng Liu, Huibing Zeng, Yiqun Zhang et al. (+2 more)
With the rapid development of large-scale pre-trained
language models based on
Transformer architectures, their high computational and
memory costs have become a major obstacle to deployment, especially in resource-constrained environments. Traditional
pruning methods typically depend on full gradient-based importance estimation, and they necessitate prior finetuning of the model to achieve satisfactory performance. This process often results in intolerable resource consumption. This paper proposes REP-LIE, a new approach to enable resource-efficient
pruning during the process of finetuning. REP-LIE leverages the gradients of LoRA low-rank
matrices to estimate the importance of weights without requiring full gradient computation. To address the inherent randomness in importance estimation, a stability score is introduced, serving as the basis for iterative
pruning of unimportant model parameters. The pruned model is further finetuned through lightweight updates, eliminating the need for full-parameter optimization in the process of finetuning. Extensive experiments on both medium-scale encoder models and large-scale generative models (LLaMA-7B and Mistral-7B) demonstrate that REP-LIE still achieves competitive performance compared to existing approaches.
Read the full abstract ▾
All authors Peng Liu, Huibing Zeng, Yiqun Zhang, Yang Yi, Jigang Wu
Data Structures and Algorithms
Liangchen Ge
We study the Lipschitz stability of
attention retrieval in
hyperbolic spaces. Existing methods lack deterministic guarantees on
attention-weight preservation under finite-precision representations. We introduce HCC+, a theoretical framework exploiting three properties of the Poincaré ball: exponential volume growth enabling query-independent boundary truncation; logarithmic covering radius of
hyperbolic 1-centers enabling dimension-independent critical-key identification; and a packing bound with constants independent of the
embedding dimension. We prove two deterministic guarantees: for exact
retrieval, the per-layer
attention deviation is bounded by 10% of its ideal value; for soft
attention, the total variation distance decays as $O(1/\sqrt{n})$, the rate of finite-sample variance. As a consequence of the guarding mechanism, the framework achieves a storage reduction factor of $6.1\times$ relative to FP16. We provide the first deterministic, query-independent
retrieval certificate in non-Euclidean geometry.
Read the full abstract ▾