Information Retrieval
Soft Curriculum Learning for Optimizing Fresh and Generalized Recommendations
Arnab Bhadury, Siyan Zheng, Anlan Yu et al. (+6 more)
Large-scale recommender systems, particularly short-form
video platforms, are often bottlenecked by massive popularity feedback loops. In such environments, as models recommend popular items, they generate an overwhelming amount of skewed training data for "head" items. This creates a self-reinforcing cycle where
retrieval and ranking models memorize "head" item patterns at the expense of generalizing across the vast "tail" of the catalogue. While Curriculum Learning (CL) offers a powerful mechanism to break this feedback loop by systematically exposing models to progressively more difficult and less frequent examples, its adoption in industrial recommendation has been hampered by hardware utilization inefficiencies or the needs for complicated pre-processing techniques because dynamic data rejection
algorithms tend to starve hardware accelearators (TPUs/GPUs) by becoming largely CPU-bound. In this work, we introduce a scalable Soft Curriculum Learning framework designed specifically for continuous training setups within industry-scale
retrieval and ranking models. By utilizing loss annealing and in-graph weight adjustments rather than rigid data filtering, we break the popularity feedback and enable dynamic curriculum pacing without sacrificing system throughput. We demonstrate empirical evidence through applications across sequence-based
retrieval models (such as SASRec), two-tower
retrieval models, and large-scale continuous ranking models. Online A/B tests on our short-
video platform demonstrate substantial lifts in both overall user satisfaction and fresh content consumption, all without degrading model throughput.
Read the full abstract ▾
All authors Arnab Bhadury, Siyan Zheng, Anlan Yu, Palaksh Rungta, Jiawei Li, Changping Meng, Dapeng Hong, Chuan He, Onkar Dalal
Machine Learning · Cross-listed from stat.ML
Distribution of hitting times for dissipative random dynamical systems on $\mathbb{R}^d$, with application to stochastic gradient descent
Stéphane Galatolo and Stéphane Chrétien
Machine Learning and more specifically Deep Learning involves solving large scale nonconvex optimization problems. Several
algorithms have been proposed in the literature, that seem to achieve satisfactory practical efficiency for difficult instances, the
Stochastic Gradient Method being the most rudimentary, while still outperforming more recent
algorithms at a number of learning tasks. A major open question about the current methods used in deep learning is to understand their convergence properties. Following a line of previous works about the long time behavior of gradient-type
algorithms, %and in particular the recent contributions from Azizian et al., we present a new approach for studying the asymptotic properties of a wide family of methods from an ergodic theoretical viewpoint. Our main results include a study of the expected time for a
stochastic optimisation
algorithm to reach a certain small neighborhood of a minimizer and show that this reaching time distributes exponentially around its average, which is given by the inverse of the stationary measure of the target. The assumptions on the
Stochastic Gradient noise include the Gaussian and the Sub-Exponential assumptions.
Read the full abstract ▾
Computers and Society
Political Sorting Can Drive AI Models Apart Through User Feedback
Petter Törnberg, Michael Heseltine, Nicolò Pagan et al. (+3 more)
Large
language models are rapidly becoming an important source of political information. This raises a fundamental question: will AI systems support a shared basis for political knowledge, or lead different political groups to rely on increasingly different models? Political sorting can drive model fragmentation if three conditions hold: politically different users select into different models, learning from user feedback pushes those models apart politically, and the resulting differences shape subsequent model choices. We call this self-reinforcing process the Centrifugal
Alignment Spiral. We study its components in three steps. First, we draw on a human experiment showing that political identity predicts model choice. Second, we fine-tune
language models on synthetic feedback reflecting predominantly Democratic or Republican preferences. Across five independent runs per model family, paired models diverged on 12-41% of unseen survey questions with large partisan gaps, and in every run the differences moved in the expected political direction; for some models, differentiation extended even to issue areas excluded from training. Pooling feedback across groups instead suppressed divergence. Third, an empirically anchored
agent-based model shows what follows when political sorting and model adaptation operate together: models attract politically distinct audiences, learn from them, and diverge further. User feedback can therefore turn political sorting among AI users into durable differences between the models on which they rely for political information.
Read the full abstract ▾
All authors Petter Törnberg, Michael Heseltine, Nicolò Pagan, Christopher Bail, Michelle Schimmel, Christopher Barrie
Cryptography and Security
Quantum-Ready Secure WAN: A Risk Assessment and Migration Framework
Saeed Alam
Enterprise wide-area networks (WANs) use
quantum-vulnerable public-key cryptography to authenticate peers and establish keys for Internet Protocol Security (IPsec), Transport Layer Security (TLS), and software-defined WAN services. Harvest-now, decrypt-later collection already threatens data whose protection lifetime may exceed the time needed to migrate, while a future cryptographically relevant
quantum computer would also endanger certificates and other authentication dependencies. Post-
quantum standards and government directives now define
algorithms and transition milestones, but they do not tell an enterprise which WAN services to migrate first or what evidence is sufficient for deployment. This paper proposes a vendor-neutral framework that separates exposure priority, migration readiness, and evidence confidence, and maps those outputs to staged security, operational, and governance gates. It also defines a complete evaluation design for classical and ML-KEM hybrid key establishment in TLS 1.3 and IKEv2/IPsec. The retained artifact is narrower: it contains author-reported aggregate TLS p50, p95, and p99 latencies at configured loss settings of 0%, 1%, 3%, and 5%, an arithmetic checker, and limited environment and MTU/MSS notes. At those settings, the TLS-H minus TLS-C p95 differences are 0.00, 0.16, 0.38, and 0.63 ms, corresponding to 0.00%, 1.32%, 3.07%, and 5.00% relative to TLS-C. These values are descriptive aggregate observations, not inferential results, because per-trial data, sample counts, original captures, and timestamped logs were not retained. Protocol-size and MTU/MSS calculations are reported separately from measured behavior, and unsupported IKE, resource, throughput, retransmission, and downgrade outcomes are excluded.
Read the full abstract ▾
Computational Complexity · Cross-listed from math.PR
The Scaling Window of Random $k$-SAT
Gaia Carenini
We prove a general upper bound for scaling windows of sparse monotone covering problems. From that, we deduce that for every fixed value $k\geq 3$, the window of random $k$-SAT is $O(n/\log n)$, improving the Friedgut-Bourgain bound of $O(n/\log\log n)$. We also show that random signed Not-All-Equal-$k$-SAT and hypergraph non-two-colourability (Property B) have windows of the same order. Our upper bound for scaling windows of sparse monotone covering problems follows from a general strategy combining the strengthening of Bourgain's sharp threshold
theorem by Keevash, Lifshitz, Long, and Minzer with a local-to-random replacement principle. This provides a systematic method for proving scaling-window bounds, addressing a question of Perkins.
Read the full abstract ▾
Cryptography and Security
Who Assures the Verifier? An Executable Assurance-Locus Audit of the European Digital Identity Wallet
Anton Sokolov
The European Digital Identity Wallet (EUDI Wallet) architecture places material duties on relying parties: they register services and intended uses, authenticate to Wallet Units, validate presentations and trust anchors, and make risk-based status decisions. Wallet certification and the emerging Functional Conformance Assessment Framework provide increasingly structured wallet-side evidence. A different question remains: what independently rerunnable evidence shows that the concrete relying-party verifier version used in a transaction enforced the applicable request, presentation and reliance-decision controls? We conduct an assurance-locus audit of current law, Architecture and Reference Framework (ARF) 3.0.0, ETSI metadata, FCAF scope and three pinned open-source verifier codebases. We then design a 17-rule research profile, a machine-readable evidence receipt and 36 frozen synthetic transactions. Three heterogeneous study-authored implementations (Python, JavaScript and jq) execute 108 cases with zero oracle mismatches and zero cross-path disagreements. The experiment establishes determinism and implementability of the proposed decision model, not product conformance or certification. Source inspection finds substantial protocol-verification mechanisms in all three public codebases but no single audited evidence object joining RP registration and purpose, exact verifier/policy version, transaction verdict and downstream attribute use. We therefore propose an RP-as-system-under-test evidence unit that complements, rather than displaces, wallet certification, registration and supervision. A preregistered census of 26 appointed experts is prepared to test content validity and governance feasibility; recruitment awaits the applicable ethics/data-protection determination.
Read the full abstract ▾
Information Retrieval
A Semantic Approach to the Academic Publishing Network: Document Vector Representations and Hybrid Structural-Semantic Fusion over OpenAlex Data
Robert Šamárek and Radek Martinek
Structural graph analysis of the academic publishing network captures the topological relationships between entities but does not see the content of works. Building on our structural approach, this work complements it with a semantic layer and a parameterized structural-semantic fusion. We represent scientific documents by citation-informed vector
embeddings (SPECTER2) and store them in an embedded vector database keyed by the stable OpenAlex ID, so that they connect directly to the graph layer. We define a modular late-fusion function that combines semantic similarity (cosine of
embeddings) and structural similarity (bibliographic coupling) with a tunable weight alpha whose value is chosen according to the specific task. On the corpus of VSB - Technical University of Ostrava we show two things: citation-informed
embeddings agree with the expert OpenAlex topical taxonomy better than a TF-IDF baseline, and in a recommendation use case the structural, semantic, and combined signals carry information in different regimes depending on the available data. Hybrid fusion here is not a universally better method but an explicit mechanism for steering complementary signals according to the task. We release the whole approach as an open-source extension of the apnet library with a reproducible workflow.
Read the full abstract ▾
Machine Learning
MSA-CITE: A Co-Adapted LoRA Specialist Ecology for Fixed-Budget Small-Model Inference
Ruitong Li, Binjie Guo, Aisheng Mo et al. (+3 more)
Compact
language models are typically deployed by retaining a single post-training checkpoint and sampling it repeatedly. In this work, we challenge this practice by treating multiple discarded checkpoints as composable assets for deployment. Starting from a single Qwen3-4B backbone, we preserve four frozen LoRA branches, each derived from a different post-training trajectory. stead of drawing four generations from one branch, we allocate a fixed four-generation budget by sampling one completion from each branch. Our method, Multi-path Specialist Adaptation with Calibrated Inference-Time Evidence (MSA-CITE), processes the resulting portfolio by grouping terminal answers into equivalence classes, scoring each class via summed calibration-derived source priors, and selecting a representative under deterministic tie-breaking rules. The readout stage does not learn from evaluation results, nor does it introduce additional generations, verifiers, or reranking steps. On 200 held-out mathematics items, the four-path portfolio achieves 65.5% accuracy, compared with 62.0% for the strongest single-branch baseline. On a 100-item subject-disjoint shift, it attains 42.0% versus 40.0%. Under in-distribution conditions, the improvements over homogeneous SFT and Online-OPD repetition are robust; results against the strongest baseline and under shifted conditions are not conclusive. Our findings offer a narrow but concrete contribution: post-training branches, even without co-training, can be collectively beneficial for deployment.
Read the full abstract ▾
All authors Ruitong Li, Binjie Guo, Aisheng Mo, Guowei Su, Jie Li, Ru Zhang
Machine Learning
Beyond Imitation: Auditing the Recoverability of Reasoning in Distilled Models
Ruitong Li, Binjie Guo, Aisheng Mo et al. (+4 more)
A correct teacher solution becomes useful supervision when the receiving student can continue its
reasoning. We measure this compatibility with prefix recovery: after revealing 25%, 50%, or 75% of a verified solution, we test whether the student completes it correctly. We connect recovery to the cosine conflict between cross-
entropy and reverse-KL gradients over the full vocabulary. Across adjacent Qwen3 teacher-student pairs from 0.6B to 8B parameters, reverse-KL
distillation delivers its most consistent mathematical and code improvements for the two students below 2B parameters. On a fixed cohort of 1,000 trajectories, average prefix recovery rises from 71.0% to 91.9% as student size increases from 0.6B to 4B, and the robust-fragile recovery gap contracts from 46.0 to 14.4 percentage points. With the teacher fixed at 8B, conflict separation falls from 0.993 to 0.233. An independent objective intervention finds the largest reverse-KL rescue on fragile trajectories. The three measurements locate the same capacity-dependent transfer regime: distribution matching has the greatest headroom when correct traces remain unevenly recoverable. Prefix recovery provides a practical diagnostic for selecting costly distribution-level
distillation.
Read the full abstract ▾
All authors Ruitong Li, Binjie Guo, Aisheng Mo, Guowei Su, Han Wang, Jie Li, Ru Zhang
Information Theory
When to Stop? Dynamic Early Termination of Sequential Ensembles
Paul Bezner, Felix Krieg and Stephan ten Brink
Ordered-statistics decoding (OSD) post-processing substantially improves the performance of belief propagation (BP) ensembles, but it also removes their natural syndrome-based stopping criterion. The high computational complexity of ensemble decoding and OSD can be reduced by sequential activation of ensemble members paired with an early termination. Instead of a syndrome-based termination we therefore apply dynamic ensemble termination (DET) to sequential ensembles: members are evaluated one at a time and decoding stops when the estimated risk that an unseen member would correct the current decision falls below an offline-fitted threshold. With hardware-oriented design in mind, we instantiate the framework with layered normalized min-sum component decoders, a row-boosted ensemble, conditional low-order OSD on the dual code, and a conventional low-cost decoder gate. A decision tree estimates the residual risk from statistics of the current candidate list. Member-dependent thresholds then target a prescribed frame error rate (FER) loss. We validate this framework on mutliple IEEE 802.11 low-density parity-check (LDPC) codes with blocklengths \(648,1296\), and \(1944\) at rates \(1/2\) and \(5/6\). At each code's design point, where the full \(64\)-member list reaches an FER of \(10^{-3}\), the DET decoder processes \(1.04\) to \(1.15\) members on average. On the \((648,540)\) code, it reduces BP work by \(39\times\) and OSD activations by \(18\times\) against the full list while retaining an signal-to-noise ratio (SNR) gain of about \(0.4\,\mathrm{dB}\).
Read the full abstract ▾
Machine Learning
Bridging the Data Gap: Digital Twin as a New Paradigm for AI-based Radio Sensing
Éloi Sainte-Beuve, Guillaume Larue, Louis-Adrien Dufrène et al. (+2 more)
We present a methodology that places a 3D digital twin (DT) of the environment as the main enabler behind the development of
radio sensing at scale. The DT acts as a world model, providing geometry, materials, and transmitter/receiver placements to a ray-tracing engine that generates time-indexed channel impulse responses (CIRs) for large numbers of plausible scenes (moving people and objects, layout variants, seasonal/weather conditions, etc). From these synthetic sequences, we train a sequential neural network that maps CIR time series to spatial occupancy estimates, enabling device-free localization (DFL) without instrumented targets. We posit that sensing is best approached as an environment-conditioned learning problem: rather than seeking a single global model, we advocate training or fine-tuning local models specialized to a site-specific DT. As a first experiment, we introduce a novel State Space Model architecture, trained and evaluated across multiple room geometries. The localization performances obtained demonstrate the potential of the approach.
Read the full abstract ▾
All authors Éloi Sainte-Beuve, Guillaume Larue, Louis-Adrien Dufrène, Quentin Lampin, Ali Al Khansa
Artificial Intelligence
Improved Multiplayer Bandit Algorithm for Bernoulli Rewards
Khang Nguyen, Ricardo Parada and William Chang
We study the multiplayer multi-armed bandit problem with information asymmetry under Bernoulli rewards, for three information structures: asymmetry in actions, in rewards, and in both. Replacing the Hoeffding-style confidence intervals of prior work with Kullback–Leibler (KL) divergence-based bounds gives strictly tighter regret guarantees in each case. We propose mKL-UCB, mKL-UCB-Intervals and mKL-DSEE, and show that the improvement factor is at least two by Pinsker's inequality and far larger when reward means are near zero or one. For asymmetry in rewards we prove that two arms' KL intervals separate after a deterministic number of samples, and that $M$ independent players accelerate elimination further.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ME
When Unpaired Sets Support Shared-Corruption Calibration: Moment Geometry and Two-Sample Precision
Shuheng Cao, Zhenhao Zhang, Ruiqi Chen et al. (+5 more)
Collections of diverse observations often share one acquisition, processing,
geometric, or channel corruption, while only an unpaired clean reference set is available. For a prescribed low-dimensional correction shared across observations, the observed and clean reference sets support inference only through the response of fixed moments. We formulate this problem as two-sample moment calibration and report a rank-aware information state combining local rank, scaled moment sensitivity, source-separated covariance, and a moment compatibility residual. Full rank gives local moment identifiability, whereas kernel directions remain unresolved to first order. A unified linearization separates observed-set and reference-set uncertainty. Under covariance weighting, the weakest scaled singular value determines worst-direction asymptotic amplification. For an orientation-preserving planar-similarity correction shared across observations, ensemble centroids and a nonzero third-order complex moment yield closed-form global population identification of translation, rotation, and isotropic scale under matched-population and no-clipping assumptions. Controlled validation tests the predicted $N^{-1}$ and $\sigma_{\min}^{-2}$ laws, Gaussian efficiency, and interval coverage. Bounded applications report color corrected-output quality, channel magnitude-response calibration, and a separate paired
geometric de-beautification result. The framework therefore reports missing or weak information instead of treating every fitted correction as identified.
Read the full abstract ▾
All authors Shuheng Cao, Zhenhao Zhang, Ruiqi Chen, Renjie Cao, Siyu Zhang, Zhaoxiang Feng, Lingwei Dang, Haoyang Wu
Computation and Language
Beyond Static Charts: Can Language and Vision Language Models Generate Interactive Data Visualization Interfaces?
Mizanur Rahman, Aaryaman Kartha and Enamul Hoque Prince
Data visualization is central to analytical
reasoning, but real-world analysis increasingly requires
language-driven interactive interfaces rather than static charts. Although recent large
language and
vision language models (LLMs/VLMs) have shown promise in generating static charts from natural
language, their ability to generate interactive data visualization interfaces remains largely unexplored due to the lack of
benchmarks. We introduce VIS-GEN, a
benchmark for evaluating how well LLMs/VLMs can generate interactive visualization interfaces from natural
language queries. VIS-GEN comprises 3,042 samples covering diverse analytical intents, including data filtering, temporal analysis, and visualization editing, each paired with
dataset metadata and natural
language queries that are designed to reflect realistic, goal driven data exploration scenarios. We
benchmark 14 state-of-the-art open-source and closed-source LLMs/VLMs, revealing large performance gaps and frequent failures on queries involving implicit intent, multiple interaction alternatives, and complex editing operations, highlighting interactive interface generation as a key open challenge beyond static chart synthesis. To address this, we propose a structured multi stage interface generation framework that decomposes the task into visualization design representation, generation of multiple interface candidates, constraint-aware critique, and self-refinement. This approach improves the best models pass rate by 15.9 percentage points, demonstrating a practical path toward more reliable
language-driven interactive visualization systems. We release VIS-GEN at https://github.com/vis-nlp/VIS-GEN.
Read the full abstract ▾
Artificial Intelligence
RCShift: Certifying When Partial Linkage Suffices for Finite-Sample Decisions
Shuheng Cao, Ruiqi Chen, Zhenhao Zhang et al. (+5 more)
Systems with costly gold outcomes and cheaper auxiliary observations must decide how much record linkage to retain. Complete pairing retains every joint counter, while separate margins retain none. Neither endpoint is calibrated to a declared finite-sample decision. Universal reconstruction can retain cycle directions invisible to the likelihood-ratio family. Family-exact storage can exceed what the decision requires because certified residual loss may fit within finite-sample slack. We introduce RCShift, which certifies two routes to sufficiency under a declared observation contract. Its exact mode characterizes minimum-cost family-exact storage through LR-visible cycle directions. Its approximate mode bounds reverse Le Cam deficiency. Its integer mode certifies whether a chosen set preserves the full experiment's minimum integer record count at specified size and power. In a rank-two witness, one aligned counter preserves a four-record minimum. An equal-cost misaligned counter and the margins require eleven records, while universal reconstruction requires two counters. A local perturbation has positive reverse deficiency yet retains the four-record minimum. Proof-checked scheduling bounds instantiate the contract before gold computation and yield exact reconstruction on the admitted tree support. RCShift turns partial-linkage storage into decision-calibrated measurement design for the declared family, costs, target, and common strictly positive support.
Read the full abstract ▾
All authors Shuheng Cao, Ruiqi Chen, Zhenhao Zhang, Renjie Cao, Siyu Zhang, Lingwei Dang, Jiajun Zhang, Tingting Dan
Computer Vision
LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment
Ziheng Jia, Zicheng Zhang, Jiaying Qian et al. (+2 more)
Aligning with the human visual system~(HVS) in perceiving and evaluating the quality of visual signals is a central objective of machine-
vision-based visual quality assessment systems. With the rapid progress of large multi-modal models~(LMMs), visual question answering provides a promising paradigm for building unified foundation models for visual quality assessment under multi-modal and multi-task scenarios. Inspired by the classical “perception-decision" process in HVS-based quality evaluation, we formulate visual quality assessment for LMM-based machine
vision as two complementary tasks: “quality interpretation” and “quality scoring". Centered on these objectives, we propose LLaVA-Assessor, a unified data construction and model training system. To support multi-modal inputs, we design an adaptive model architecture that enables efficient processing of both images and
videos. For data construction, we develop rigorous human annotation protocols and a novel machine-synthesis-dominated data expansion pipeline to build a large-scale and high-quality
datasets. Furthermore, we introduce a simple yet effective
prompt disentanglement strategy to alleviate training-objective confusion in multi-task learning, thereby enabling stable and coherent joint training. The resulting all-in-one LMM LLaVA-Assessor-GIGA achieves superior performance on $11$ image/
video quality scoring test sets and 4 visual quality interpretation
benchmarks. Extensive results demonstrate the effectiveness of integrating structured data construction, adaptive model design, and multi-task joint training for automated visual quality assessment. Our work provides compelling insights for developing foundation LMMs for automatic visual quality assessment. Project page at https://github.com/jzhws/LLaVA-Assessor.
Read the full abstract ▾
All authors Ziheng Jia, Zicheng Zhang, Jiaying Qian, Guangtao Zhai, Xiongkuo Min
Numerical Analysis
Runge–Kutta-Aligned Oscillation Elimination: Restoring Superconvergence for Fully Discrete Shock-Capturing DG Schemes
Manting Peng, Zhuoyun Li and Kailiang Wu
Nonlinear stabilization is indispensable for discontinuous Galerkin (DG) discretizations of
hyperbolic conservation laws, yet it typically disrupts the delicate error structure required for superconvergence analysis. Consequently, existing theory has largely been restricted to linear or semi-discrete schemes lacking oscillation control. This paper bridges this gap by proposing a Runge–Kutta (RK) aligned oscillation-eliminating (OE) DG framework that restores the superconvergence properties. By synchronizing the pseudo-time step in the OE procedure with the cumulative RK stage coefficients, we unlock a cancellation mechanism for low-order interface errors that is inaccessible to standard OEDG formulations. We rigorously prove that this fully discrete scheme achieves $(k+2)$-th order superconvergence to a tailored projection of the exact solution for linear conservation laws in both one and two dimensions, while maintaining the non-oscillatory shock-capturing capabilities of the original method. Moreover, we establish a general guiding principle for designing a class of OE-type DG schemes that exhibit such superconvergence. Key theoretical innovations include the construction of stage-aligned correction functions to compensate for nonlinear OE sources and the discovery of a two-dimensional projection operator that preserves
outflow-edge averages, a property essential to close the discrete shift estimates. Numerical experiments confirm the predicted superconvergence rates and demonstrate that RK
alignment preserves the parameter-free robustness of OEDG for problems with strong discontinuities.
Read the full abstract ▾
Artificial Intelligence
TREND-10K: A Comprehensive Dataset for Next-Generation Video Quality Assessment Based on Preference-Driven Media
Ziheng Jia, Zicheng Zhang, Junqi Zhang et al. (+4 more)
The increasing prominence of short-
video platforms, coupled with the advanced commercialization of AI-generated content (AIGC)
videos, has led to a shift in the types of
video media trend consumed by users in their daily lives. Traditional user-generated content (UGC) is gradually being replaced by professional short dramas and AIGC entertainment. Consequently, VQA for contemporary media content has become increasingly important. This requires a unified evaluation framework that can handle diverse
video content and evolving media trends. In this context, we introduce TREND-10K, a next-generation comprehensive VQA
dataset consisting of the trend-driven part and the static part, containing $10,000$
videos across a wide spectrum of content types. The trend-driven part is based on the TREND-Search framework, which captures user preference profiles from trending lists on online platforms and formulates sampling strategies based on these profiles. The static part, on the other hand, is composed of supplementary samples selected from publicly available
datasets. To support unified evaluation for various
video types, we incorporate three evaluation dimensions: technical, aesthetic, and AIGC-trace. Experiments show that our
dataset ensures high annotation quality and exhibits remarkable generalization across multiple content categories. In conclusion, our work presents a robust framework for advancing VQA, addressing challenges caused by the temporal
evolution of user perceptual habits and preferences.
Read the full abstract ▾
All authors Ziheng Jia, Zicheng Zhang, Junqi Zhang, Jiaying Qian, Jiarui Wang, Yushuo Zheng, Xiongkuo Min
Computation and Language
Magnitude Profile Pruning: Calibration-Free Structured Attention Head Removal for Transformer Compression
Kasun Dewage, Marianna Pensky, Heranga K. Rathnasekara et al. (+1 more)
Structured
pruning of
attention heads provides a hardware-friendly way to compress
Transformer language models. However, existing methods for measuring head-level importance require calibration data, gradient computation, or Hessian estimation. These requirements add extra overhead and make the methods depend on the data. Our work presents Magnitude Profile (MP) scoring, a training-free criterion for head importance that identifies dispensable heads through statistical outlier detection on weight row norms. Heads whose projection weights fall within the population bulk are pruned, while heads exhibiting outlier norms, which carry disproportionate representational capacity, are preserved. Our work further gives MP-G, a variant that handles Grouped Query
Attention (GQA) by distributing shared key-value group scores across associated query heads. Across five models evaluated on WikiText-2 perplexity at 12.5%-50% head sparsity, MP-G achieves the best perplexity on OPT-6.7B at all sparsity levels (18.46 at 12.5%, 27.87 at 25%, 152.0 at 50%). MP-G also gives the best results on RoBERTa-large at 12.5% and 25% sparsity, with perplexity values of 7.27 and 10.28, outperforming calibration-dependent baselines including Wanda-Head, SparseGPT-Head, and Gradient-Head. It requires zero forward passes, calibration samples, or gradient computation. At 50% sparsity, head
pruning yields up to 16% parameter reduction with 50%
attention FLOP savings. Our results show that weight-only statistical scoring can match or outperform data-dependent methods for structured head
pruning, providing a practical, zero-cost criterion for
Transformer compression.
Read the full abstract ▾
All authors Kasun Dewage, Marianna Pensky, Heranga K. Rathnasekara, Suranadi De Silva
Human-Computer Interaction
TRACE: Transparent Retrieval for Abstract Concept Evaluation
Joseph Bingham
Recent work reports that
vision–
language models (VLMs) struggle to establish and maintain stable reference in repeated reference games. Rather than ask which VLM does best, we ask a more basic question: do you need a large pretrained VLM for this at all? On grounding a single director utterance to one of twelve tangram silhouettes, we compare six off-the-shelf VLMs against a transparent baseline that uses no learned visual representation: classical SIFT keypoint matching and a signal-quality index over retrieved images. On identical trials, the transparent baseline matches the strongest VLM (SigLIP-large) and significantly outperforms the other five, including every CLIP and OpenCLIP variant. The baseline additionally retrieves external images, so this is not a matched-information comparison; what it shows is that a learned visual representation is not the bottleneck for this task: given retrieved images, a shape-appropriate classical similarity suffices. Along the way we find that abstract-grounding ability varies widely across VLMs (15–39% top-1; chance 8.33%, humans $\approx$77–80%), so the weakness is model-specific rather than intrinsic to contrastive pretraining; on the 1{,}013-shape KiloGram
benchmark the pattern generalizes for CLIP, with per-shape difficulty tracking human shape-nameability. The pipeline is a classical, inspectable alternative rather than a learned one. We close by sketching how an explicit, inspectable representation of listener-side pact state could carry this approach into interactive multi-turn reference, which we leave to future work. Code available in supplementary material.
Read the full abstract ▾
Machine Learning
Activation-Energy Pruning for Spiking Neural Networks: Unsupervised Personalization via Spike-Count Saliency
Joseph Bingham
Activation-energy
pruning – removing weights whose product of magnitude and cumulative pre-synaptic spike count falls below a threshold – was established as an effective unsupervised personalization strategy for conventional deep neural networks~\citep{BINGHAM2025101242}. This paper asks what happens when the same criterion is applied to spiking neural networks (SNNs), where activation energy is not merely a useful heuristic but a literal physical quantity proportional to the metabolic cost of each synapse. The answer is surprising on three counts. First, gradient-based
pruning methods that perform competitively on conventional networks (SNIP, GraSP, magnitude
pruning) consistently underperform on SNNs, collapsing to near-chance accuracy by $\sigma = 0.2$ sparsity across all tested architectures and
datasets. We trace this to a systematic incompatibility between surrogate-gradient saliency estimation and the binary spike-train representation, though we cannot rule out that alternative surrogate choices or hyperparameter settings might partially mitigate the effect. Second, activation-energy
pruning applied to a neuromorphic
benchmark improves over the source model at high sparsity ($98.4 \pm 0.4\%$ vs.\ $97.2 \pm 0.7\%$ at $\sigma = 0.8$ on N-MNIST), a phenomenon with no counterpart in the conventional network setting. We interpret this result as consistent with experience-dependent cortical specialisation: removing connections active only for non-target classes may reduce cross-class interference and produce a cleaner target representation, though we note this is an interpretive analogy rather than a mechanistic demonstration.
Read the full abstract ▾
Artificial Intelligence
Toward User-Mediated Self-Repair in Ubiquitous Robots Through Goal-Oriented Agentic AI
Morten Roed Frederiksen
Ubiquitous robotic systems often lack traditional visual interfaces, necessitating resilient natural
language interaction for maintenance and repair tasks. This paper presents a goal oriented agentic AI architecture designed to enable non-expert users to perform technical repairs through situated dialogue. The framework utilizes a multi-layered approach that decouples high-level strategic planning from reactive conversational execution to transform unconstrained human instructions into a structured hierarchy of goals. We conducted a study involving twenty participants to evaluate the system's efficacy using a physical hardware testbed. The architecture achieved a 95% task completion rate, and participants reported positive self-efficacy following real-time guidance that adapted to conversational diversions and linguistic variations. A comparative analysis with an online baseline revealed that the transition to a physical environment significantly decreased perceived social presence (p=.0005), and trust and competence, (p=.037), while the agentic framework remained robust throughout the interaction. These findings indicate that goal oriented agentic AI can support the sustainability of body-worn technologies by empowering users to perform critical maintenance in ubiquitous contexts.
Read the full abstract ▾
Computation and Language
AI-inferred expressed well-being and collective-action discourse in climate-change campaigns on X
Wentao Xu
Climate campaigns are often evaluated through
attention and mobilization, but less is known about the well-being
language that accompanies them. Whether campaign periods alter positive affect and hope, and whether happiness aligns with action
language, remains unresolved. We analysed 364,118 public Twitter/X posts from Earth Day, Earth Hour, Global
Climate Action Day and World Environment Day in 19 occurrence-years, using 30-day pre-event, event and post-event windows. A versioned weighted lexical model estimated happiness, future-oriented hope, collective capability, distress and action
language. Event-period happiness prevalence was 9.02 percentage points higher than the pre-event baseline , whereas paired occurrence contrasts showed a 10.75-point decline in action
language, indicating a happiness–action divergence. The happiness estimate remained positive across composition and text-deduplication checks, but was less precise under a 19-cluster wild bootstrap. Happier source posts had lower odds of an observed matched retweet cascade.
Read the full abstract ▾
Machine Learning
Evaluating LLM-Generated Rules for Heart Disease Prediction
Feisal Alaswad, Batoul Aljaddouh, Maher Alrahhal et al. (+2 more)
This study compares traditional machine learning models and Large
Language Model (LLM)-generated rule-based systems for heart disease prediction using the UCI Heart Disease
dataset. Several classifiers, including Logistic Regression, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Naive Bayes, Decision Tree, and Random Forest, were evaluated alongside rule-based systems generated using GPT-4o and Claude Sonnet 4.6. Model performance was assessed using accuracy, precision, recall, and F1-score metrics. Experimental results show that traditional machine learning models consistently outperform LLM-generated rule-based systems in predictive performance. Random Forest achieved the best overall performance with 90.2% accuracy, a precision of 0.829, perfect recall of 1.0, and an F1-score of 0.906. Naive Bayes followed closely with 88.5% accuracy and an F1-score of 0.881. In contrast, the LLM-generated rule models achieved lower performance, with Claude Sonnet 4.6 reaching 80.3% accuracy (F1-score: 0.833) and GPT-4o obtaining 70.5% accuracy (F1-score: 0.690). Despite the performance gap, the LLM-generated rules provide interpretable IF-THEN diagnostic logic that enhances explainability and transparency in clinical decision-making. These findings highlight the trade-off between predictive performance and interpretability in medical artificial intelligence systems. The complete implementation of all experiments, including machine learning models and LLM-derived rule classifiers, is publicly available in the GitHub repository at https://github.com/FeisalAlaswad/LLM-Rule-ML-Heart-Disease-Prediction .
Read the full abstract ▾
All authors Feisal Alaswad, Batoul Aljaddouh, Maher Alrahhal, Wafaa Al Nassan, Talal Bonny
Machine Learning
Early Prediction of Satellite Collision Probability Using a Hybrid TCN-Transformer Model for a CDM-Based Conjunction Analysis Framework
Rabia Tüylek Tok, Burak Yağl{\i}oğlu, Enes Dağ et al. (+1 more)
The rapid expansion of operational satellites and orbital debris has increased the frequency of close approach events in low Earth orbit (LEO), creating a higher operational burden for satellite operators. This problem is especially critical for satellites using electric propulsion, where low-thrust maneuver capability imposes additional time constraints on collision avoidance planning. In current practice, Conjunction Data Messages (CDMs) provide relative state, covariance, miss distance, time of closest approach, and probability of collision (PoC) information for conjunction assessment. However, the nonlinear propagation of orbital uncertainties and the sensitivity of PoC to covariance
evolution make the interpretation of sequential CDMs challenging. This study proposes a learning-based framework for early prediction of satellite conjunction risk by estimating the PoC expected in the subsequent CDM update of the same close approach event. In the proposed methodology, an Unscented Transform-based propagation and backpropagation framework is first used to evaluate the sensitivity of the collision risk metric to CDM parameters. In addition, Principal Component Analysis is applied to the numerical CDM parameters to identify the features most relevant to PoC variation. The results obtained from the sensitivity analysis and PCA are then used to justify the selected raw CDM parameters and to construct derived metrics representing relative motion, encounter geometry, and covariance-related uncertainty. Using the resulting sequential enriched conjunction
dataset, a hybrid Temporal Convolutional Network (TCN)-
Transformer model is trained to learn the temporal
evolution of conjunction risk. The framework is applied to CDMs received and analyzed within TÜBİTAK UZAY, demonstrating its potential for earlier and more consistent operational risk evaluation for LEO satellite conjunctions.
Read the full abstract ▾
All authors Rabia Tüylek Tok, Burak Yağl{\i}oğlu, Enes Dağ, Emre Onur Kahya
Computer Vision
Personalized and Explainable Blood Pressure Estimation from PPG via Hybrid CNN–Morphological Features
Myung-Kyu Yi, Jongshill Lee, Jeyeon Lee et al. (+1 more)
Continuous cuffless blood pressure (BP) monitoring using photoplethysmography (PPG) offers a promising solution for personalized healthcare. However, existing methods have two major limitations. Handcrafted feature-based approaches rely on precise fiducial point detection and are limited to short-term analysis, while deep learning models, despite their accuracy, often operate as black boxes with limited physiological interpretability. To address these challenges, we propose a physiology-guided hybrid framework for personalized BP estimation that couples a convolutional neural network (CNN) branch capturing global and local waveform dynamics with a morphology-prior branch that explicitly encodes person-specific vascular characteristics. By
embedding a morphology-based feature set that explicitly encodes individual vascular characteristics, the proposed framework enhances personalization and reduces dependence on large-scale training
datasets. Evaluated on a subset of the MIMIC-III database under a subject-specific (personalized) testing protocol, the proposed personalized physiology-guided hybrid approach achieved mean absolute errors (MAEs) of 3.77 mmHg for systolic BP and 2.36 mmHg for diastolic BP, corresponding to relative improvements of 43.7% and 32.4% over a subject-specific (personalized) CNN-only baseline. SHAP-based analysis confirmed that the introduced morphology-prior features align with individual vascular characteristics, reinforcing per-subject interpretability. These findings highlight the potential of personalized, physiology-guided hybrid learning with novel morphological descriptors for accurate and explainable BP monitoring in real-world settings.
Read the full abstract ▾
All authors Myung-Kyu Yi, Jongshill Lee, Jeyeon Lee, In Young Kim
Machine Learning
On-Device Language Models for Privacy-Preserving Stress Prediction: A Multimodal Evaluation on Mobile Health
Ibukunoluwa Soyebo, Alyssa Donawa, Rodrigo Aguilar Barrios et al. (+2 more)
Stress is a pervasive determinant of mental health and a key target for mobile health interventions. On-device
language models (ODLMs) offer
privacy-preserving inference without cloud dependency, yet their feasibility for health prediction under mobile resource constraints remains underexplored. We evaluate ODLMs for multi-modal stress prediction using zero-shot prompting, measuring predictive accuracy alongside latency and throughput. Our results show that objective sensor features marginally outperform subjective self-reports on average, and that lightweight sub-2B models achieve low latency with predictable resource usage. Our findings highlight both the promise and the practical constraints of ODLMs for mobile mental health.
Read the full abstract ▾
All authors Ibukunoluwa Soyebo, Alyssa Donawa, Rodrigo Aguilar Barrios, Brice Patchou, Corey E. Baker
Computational Engineering
Dynamic Windowing in Transformers via Regime Incorporation for Financial Time Series
Praveen, Prince Chouhan, Keshav Maheshwari et al. (+1 more)
Financial time series exhibit non-stationary behavior, where the strength and extent of temporal dependencies vary across
market regimes. Trending, low-
volatility phases typically require long-range contextual information, whereas mean-reverting, high-
volatility periods rely more heavily on short-term dynamics. Standard
Transformer architectures, with fixed
attention windows and static positional encodings, are therefore unable to adapt to such variations. In this work, we propose a regime-aware dynamic windowing framework that incorporates
market regime information directly into the
Transformer. We construct four generic regime signals from price series:
volatility ratio, trend strength, local predictability ratio (LPR), and rolling autocorrelation. We incorporate these signals into the model through two mechanisms: (i) regime-augmented inputs to a standard
Transformer architecture, and (ii) a modified
attention layer that modulates
attention weights using regime
embeddings. Experiments on five S&P 500 stocks show consistent improvements across five evaluation metrics, demonstrating that regime-aware dynamic windowing enhances both interpretability and predictive performance in financial
forecasting tasks.
Read the full abstract ▾
All authors Praveen, Prince Chouhan, Keshav Maheshwari, Aman Verma
Distributed Computing
Operation-Type-Aware Client Routing for Leader-Based Consensus Datastores
Sri Saran Balaji Vellore Rajakumar and James Thompson
Leader-based consensus datastores (etcd, ZooKeeper) face two competing routing goals: spread load evenly across members, and route operations to the member whose protocol role matches the operation. Writes must commit through the leader, so sending them elsewhere adds a forwarding hop. Linearizable reads need only a lightweight leader confirmation before any member can serve them locally. The upstream etcd client uses gRPC's round_robin balancer, distributing reads and writes uniformly across cluster members. An operation-aware client resolves this by pinning writes to the leader and distributing reads across the healthy read pool. In steady state on a 3-node etcd cluster (80/20 read/write mix, 5 trials), this lowers write P50 by 29% and raises throughput by 9%. When a follower degrades silently, the operation-aware client detects the latency shift and removes it from the read pool, cutting read P99 by 64%, write P99 by 74%, and raising throughput by 89%. The same routing rule applied to ZooKeeper (ZAB protocol, different implementation) points in the same direction, showing that the result follows from leader-based consensus structure rather than one system's implementation. The key obstacle to discovering this policy adaptively is that the leader confirmation round-trip occurs between cluster members, so the client sees only a blended latency signal rather than the decisive coordination cost directly.
Read the full abstract ▾
Computation and Language
Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
Yuxuan Li, Victor Zhong and Ehsan Kamalloo
Persona-driven techniques increasingly adapt large
language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid, synthetic personas that flatten individual variation, rely on stereotypes, and miss the nuanced signals driving actual human preferences. We introduce profile behavioral grounding, a framework for extracting open-ended, high-fidelity user profiles directly from authentic, anonymized social media posts. We evaluate these profiles across two paradigms: train-time personalization via supervised finetuning (SFT) and non-parametric test-time multi-perspective
reasoning. Across complex recommendation and open-ended query
benchmarks, behaviorally grounded profiles consistently improve base models and outperform synthetic profile baselines, driving stronger parametric
alignment and enabling richer, multifaceted
reasoning. Our findings establish open-ended, behavior-derived profiles as a highly diverse and effective foundation for the next generation of personalized
language systems. Our code base is available at https://github.com/ServiceNow/behavior-grounding.
Read the full abstract ▾