Information Theory · Cross-listed from eess.SP
Finite-Resolution Microwave Linear Analog Computer (MiLAC)-Aided Multiuser Beamforming
Zheyu Wu and Bruno Clerckx
Large-scale
antenna arrays are essential to future wireless networks but impose significant hardware and digital-processing burdens. The microwave linear analog computer (MiLAC) offers a promising architecture for addressing these challenges. In a MiLAC, beamforming is realized entirely in the analog domain through a reconfigurable multiport microwave network comprising tunable admittance elements. However, existing studies assume that these elements are continuously tunable, whereas practical implementations can support only finitely many configurable states. This paper investigates finite-resolution MiLAC-aided multiuser beamforming under lossless and reciprocal constraints with prescribed connectivity patterns. Each tunable susceptance is selected from a symmetric uniform finite-resolution codebook. We formulate an online problem that jointly optimizes the discrete susceptances and power allocation for a prescribed codebook, and an offline problem that designs the codebook based on channel statistics. By exploiting the odd-uniform codebook structure, we express each multilevel susceptance as a weighted sum of two-level variables and develop exact continuous penalty models for both the online beamforming and offline codebook design problems. We prove that, for sufficiently large penalty parameters, these penalty models are globally equivalent to their original discrete counterparts. Building on these formulations, we develop efficient ADMM-based
algorithms for solving the two problems. Numerical results demonstrate that the performance of an unquantized fully-connected MiLAC can be approached with substantially reduced connectivity and finite resolution. In particular, a 3-bit stem-connected MiLAC achieves more than 95% of the sum-rate performance of the unquantized fully-connected MiLAC while requiring only 22% of its tunable components.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele et al. (+1 more)
Modern probabilistic machine learning models increasingly produce multivariate outputs with complex dependence structure, from multi-step time-series forecasts to sample path predictions. Understanding which input features drive the predictive uncertainty is important for risk-aware decisions, model diagnostics, and deciding whether the uncertainty should be mitigated or hedged against. This attribution problem requires a choice of how dependencies between output components are treated. Existing approaches reduce the output to a scalar through aggregation or projection before attribution, thereby obscuring whether features affect marginal uncertainty, dependence structure, or both, while component-wise analyses can miss dependence effects entirely. We close this gap by introducing a hierarchy of three
entropy-based Shapley games that make this output-side choice explicit for any ordered multivariate outcome, ranging from per-component marginal
entropy to fully joint
entropy. The hierarchy isolates a cross-component attribution term that captures how each feature shifts the dependence between output components, a quantity invisible to component-wise methods. We establish a chain-rule decomposition of the joint attribution and characterize the cross-component term through conditional total correlation, providing both closed-form and sample-based
estimators. Finally, we demonstrate how the framework captures differences in learned joint structure across probabilistic models from distributional regression to a zero-shot time series foundation model.
Read the full abstract ▾
All authors Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele, Martin Jullum
Computers and Society
Adaptive Resource Allocation for Effective and Efficient LLM Social Survey Simulation
Yuanzi Li, Xueyang Feng, Junhao Wang et al. (+2 more)
Large
Language Models (LLMs) enable scalable social survey simulation, yet existing pipelines typically use the same strong general-purpose model and a fixed, often large, respondent history for every respondent-question request. This uniform approach overlooks three factors. First, stronger models may rely on their own knowledge rather than respondent-specific evidence while costing more. Second, additional history can help when evidence is limited, but irrelevant responses may add noise and increase input length. Third, the preferred model and history budget can depend on each other. We propose E2Sim, an adaptive resource allocation framework that jointly selects a model and history budget for each request. Given a respondent persona, ranked response history, and target question, a lightweight policy predicts the accuracy and cost of each configuration and selects the most suitable one. We use respondent-history drop-and-swap augmentation to improve robustness to incomplete or variable histories, and a margin-based curriculum that progresses from easier allocation decisions to harder ones. Experiments on four real-world social survey
datasets, multiple model pools, and different history-budget spaces show improvements over the oracle best-fixed configurations, with accuracy gains of up to 6.3 percentage points and cost reductions of up to 55.3 percent. Code is available at https://anonymous.4open.science/r/E2Sim-DE66.
Read the full abstract ▾
All authors Yuanzi Li, Xueyang Feng, Junhao Wang, Lei Wang, Xu Chen
Artificial Intelligence
ASCT: Attentive Search over Counterfactual Trees for Credit Assignment in Agentic Reinforcement Learning
Yang Li, Jinhan Yang, hai liu et al. (+8 more)
Terminal utility evaluates a complete agentic workflow, but learning requires credit for the decisions within it. We introduce Attentive Search over Counterfactual Trees (ASCT), a framework that turns training-time multi-step search into local action credit. At actor-visited states, an auxiliary tree evaluates alternative legal actions from the same recoverable prefix. Its action-value table is centered by the frozen actor's probabilities and supplies credit for PPO on actor-sampled trajectories. This protocol connects counterfactual evaluation to policy learning while deploying the actor alone. Uniform, UCT, and cost-aware AgentUCT instantiate the framework. On HotpotQA agentic
retrieval-augmented generation, all three improve mean held-out utility over trajectory-return PPO and workflow-adapted VinePPO. Across three seeds, ASCT-AgentUCT reaches 0.6187 utility versus 0.5939 for VinePPO, with gains in answer F1 and execution cost, and uses 50.3% fewer recorded auxiliary Qwen
tokens. Transfer and component-description studies examine the learned policies beyond the training setting.
Read the full abstract ▾
All authors Yang Li, Jinhan Yang, hai liu, Di Wan, Xiyu Chen, Zongsi Xu, Tuo Zhou, Sheng Zhong, Sergey Volkov, Ye Luo, Hao Sun
Machine Learning · Cross-listed from q-bio.QM
Uncertainty Quantification in Cardiac Model Personalisation from Ultrafast Ultrasound
Camilla Ferrario, Maelys Venet, Olivier Villemain et al. (+1 more)
Cardiac model personalisation requires inferring mechanical parameters that are not directly measurable in vivo. Ultrafast ultrasound shear wave elastography (SWE) enables non-invasive tracking of myocardial stiffness dynamics over the cardiac cycle, providing a target for personalisation. However, mapping these observations to subject specific model parameters remains ill-posed, as multiple parameter sets can reproduce the same stiffness dynamics. We formulate SWE-informed personalisation as a statistical inference problem using simulation-based inference (SBI). Using a subject-adapted 0D cardiovascular model and neural posterior estimation, we estimate model-conditional posterior distributions over active stiffness scale k0, contraction rate kATP, and relaxation rate kSR, conditioned on SWE-derived curve features and subject specific context. Among six healthy volunteers, four passed objective prior-support diagnostics and were retained for quantitative posterior analysis. Curve-level RMSE against the observed SWE target decreased from 12.61 $\pm$ 5.55 kPa for the prior predictive median to 1.14 $\pm$ 0.38 kPa for the posterior predictive median, an 89.7 $\pm$ 4.2% reduction. Posterior analysis revealed parameter-specific uncertainty, k0-kATP compensation, weaker constraint of kSR, and the importance of prior-predictive diagnostics for assessing whether each subject is represented within the modelled SWE feature space. These results support SBI for uncertainty aware SWE-based personalisation, while identifying prior support and forward-model adequacy as key diagnostics.
Read the full abstract ▾
All authors Camilla Ferrario, Maelys Venet, Olivier Villemain, Maxime Sermesant
Machine Learning
Adversarial Consistency-Guided Representation Learning for Multi-view Clustering
Yuchen Lin, Kunpeng Xu, Ying Fang et al. (+1 more)
Multi-view clustering aims to capture cross-view consistency while exploiting view-specific information. However, shared representations learned to capture cross-view consistency may still retain view-identifying information, potentially compromising the consistency of cross-view clustering structures. To address this issue, we propose ACGRL, an
adversarial consistency-guided representation learning framework for multi-view clustering. ACGRL employs a gradient-reversal view discriminator to reduce view identifiability and obtain invariant reference representations. These representations are then frozen to provide fixed references for disentangling view-specific information from cross-view common information in the subsequent learning stage. The fixed reference representations are concatenated with the learned view-specific representations for reconstruction and clustering, with cross-view cluster
alignment encouraging consistent clustering assignments. Experiments on four
benchmark datasets demonstrate the superior clustering performance of ACGRL compared with representative multi-view clustering methods.
Read the full abstract ▾
All authors Yuchen Lin, Kunpeng Xu, Ying Fang, Lifei Chen
Computation and Language
Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders
Zichao Yu, Qianshuo Ye, Xu Wang et al. (+1 more)
On-policy
distillation (OPD) is a widely adopted post-training technique for LLM
reasoning. It is commonly believed to transfer knowledge from a stronger teacher, yet what OPD actually distills into the student's internal representations remains unclear. We study this question with sparse crosscoders, which learn one feature dictionary shared by the student before and after OPD and the teacher. Standard crosscoder analyses, however, identify model-specific features but cannot tell how a model's use of its features changes, since all models are encoded into one set of feature activations. We therefore propose the swap readout, which reads each student checkpoint's feature activations on its own, measuring how training changes the student's use of each feature, even for checkpoints unseen by the crosscoder. Across three OPD settings, we find that OPD neither creates features nor passes on the teacher's own, and leaves the firing rates of over 98% of the student's frequently used features within 20%. We further examine the SFT warm-up on the teacher's rollouts that commonly precedes OPD and makes it more effective. Rather than adding features, the warm-up reweights the shared ones in two ways. First, it already raises and lowers many of the features that OPD later raises and lowers, doing part of OPD's work in advance. Second, it changes features that OPD alone would not, notably those for conversation format,
reasoning style, and mathematical notation, and these changes persist through OPD. Imposing this reweighting on a directly distilled student's features, without changing its weights, brings its accuracy close to that of the warmed-up student, whereas the same change on shuffled features does not. Together, these findings suggest that OPD reweights existing features rather than acquiring new ones: the student learns from the teacher how to use the features they already share.
Read the full abstract ▾
All authors Zichao Yu, Qianshuo Ye, Xu Wang, Difan Zou
Cryptography and Security
OT-PCA: New Key-Recovery Plaintext-Checking Oracle Based Side-Channel Attacks on HQC with Offline Templates
Haiyue Dong and Qian Guo
In this paper, we introduce OT-PCA, a novel approach for conducting Plaintext-Checking (PC) oracle based side-channel attacks, specifically designed for Hamming Quasi-Cyclic (HQC). By calling the publicly accessible HQC decoder, we build offline templates that enable efficient extraction of soft information for hundreds of secret positions with just a single PC oracle call. Our method addresses critical challenges in optimizing key-related information extraction, including maximizing decryption output
entropy and ensuring error pattern independence, through the use of genetic-style
algorithms. Extensive simulations demonstrate that our new attack method significantly reduces the required number of oracle calls, achieving a 2.4-fold decrease for hqc-128 and even greater reductions for hqc-192 and hqc-256 compared to current state-of-the-art methods. Notably, the attack shows strong resilience against inaccuracy in the PC oracle-when the oracle accuracy decreases to 95%, the reduction factor in oracle call requirements increases to 7.6 for hqc-128. Lastly, a real-world evaluation conducted using power analysis on a platform with an ARM Cortex-M4 microcontroller validates the practical applicability and effectiveness of our approach.
Read the full abstract ▾
Computer Vision
NucShare: Lightweight Nuclei Instance Segmentation with Foundation-Model Accuracy
Wenyan Li, Xiangyang Jia, Wenlong Zhong et al. (+1 more)
Nuclei instance
segmentation is fundamental to quantitative pathology. Yet high-accuracy methods mostly build on large
vision transformers (ViTs) or heavy convolutional backbones, whose parameter count and compute cost hinder deployment in clinical and edge settings. We present NucShare, a lightweight model whose shared decoder handles
nuclear pixel
segmentation, horizontal-vertical distance, and classification through learnable transposed convolutions for upsampling and three lightweight heads, using 37% of independent decoders' parameters with no loss in accuracy. Output-level
distillation then transfers knowledge from NucShare-T (UNI2-h) to NucShare-S (ConvNeXt V2-Tiny), reducing 690.5M parameters to 34.7M. On PanNuke they reach mPQ 0.524 and 0.519, above the prior best CFR-SAM-H at 0.511, and NucShare-S surpasses HoVer-Net and Mask R-CNN by 5.6 and 15.0 points; on zero-shot MoNuSeg it attains bPQ 0.668 against CFR-SAM-H's 0.662. Code: https://github.com/L-iMeng-L/Newidea
Read the full abstract ▾
All authors Wenyan Li, Xiangyang Jia, Wenlong Zhong, Xu Chen
Computation and Language
From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data
Husrev Taha Sencar, Rezart Beka, Danish Naeem et al. (+6 more)
Aligning
language models with a specified normative framework requires translating abstract principles into concrete examples and preference signals from which models can learn. We present an expert-driven methodology for constructing such
alignment data and apply it to a normative framework grounded in Islamic ethical, theological, and jurisprudential traditions. Over approximately one year, seven domain experts systematically probed
language models to identify
alignment deficiencies, curated desired responses, and constructed preference pairs from model outputs and expert judgments. The resulting Arabic-English
datasets contain approximately 2.8K supervised fine-tuning (SFT) examples and 5.4K preference pairs spanning a broad range of normative domains. We evaluate the
datasets through controlled post-training experiments comparing a Baseline model with models incorporating the curated SFT data alone and both the SFT and preference data. In blind expert evaluation on 150 separately constructed
prompts, the model trained with the curated SFT data was preferred over the Baseline in 51.3% of assessor judgments, compared with 14.4% in the opposite direction (p < .001 at the
prompt level). Adding the preference data resulted in a smaller difference, with the model trained with both
datasets preferred over the SFT model in 28.0% of judgments versus 20.9% in the opposite direction; this difference was not statistically significant at the
prompt level (p = .166). Standard Arabic and English
benchmarks show no broad degradation in general-purpose capabilities. These results demonstrate how expert-defined normative principles can be systematically operationalized into
alignment data and evaluated through controlled model training.
Read the full abstract ▾
All authors Husrev Taha Sencar, Rezart Beka, Danish Naeem, Seda Ozalkan, Majd Hawasly, Ji Lucas, Ala AlFuqaha, Mohamed Abdallah, Recep Senturk
Robotics
ReCAT: Remember, Count, and Time: Structured Recurrent Memory for Robot Manipulation
Pankhuri Vanjani, Mostafa Hatab, Can Mizrakli et al. (+4 more)
Memory-dependent manipulation requires
robots to make decisions using information that is no longer available to their current sensors, such as recalling an earlier visual cue, tracking task progress, counting repeated events, or estimating elapsed time. We present ReCAT, a
language-conditioned policy with structured recurrent
memory. An instruction-conditioned encoder forms features from the current observation. A recurrent
memory integrates the observation stream through Mamba-2 layers and one causal
attention layer. A flow-matching
Transformer decoder reads the current and the historical representation through separate cross-
attention in every block. ReCAT reaches 95.3% average success on LIBERO and 62.4% on RMBench, with the best or tied-best result on six of nine tasks. On three real-
robot tasks probing spatial recall, event counting, and interval timing, the best ReCAT variant reaches 66.7% average success, against 8.3% for the strongest short-history baseline. Controlled comparisons within ReCAT show that the observation encoder and every-block
memory conditioning are needed for this performance. They also show that update rules developed for efficient sequence modeling behave differently as
robot memory: additive updates have the highest observed success on counting and timing, and delta-rule updates on spatial recall. Project website is at https://intuitive-
robots.github.io/ReCAT
Read the full abstract ▾
All authors Pankhuri Vanjani, Mostafa Hatab, Can Mizrakli, Vaisakh Shaj, Zhuoyue Li, Moritz Reuss, Rudolf Lioutikov
Cryptography and Security
Trajectory-Level Security Debt in LLM Coding Agents
Prateek Kumar Rajput, Abdoul Kader Kabore, Yewei Song et al. (+4 more)
LLM coding
agents can traverse hundreds of intermediate code states before submitting a solution. Evaluating only the final artifact leaves the
evolution of security findings unmeasured. We introduce the Security Debt Line Integral (SDLI), which accumulates static-analysis risk when an
agent reaches a new best test pass ratio. We instantiate it with four static application security testing (SAST) tools and study artifacts from 830 passing SWE-bench runs, 712 ProgramBench final workspaces, and 13 public MirrorCode trajectories. The two large populations use the final-state special case of SDLI. Two-tool Common Weakness Enumeration (CWE) class agreement occurs in 3.9% of SWE-bench runs and 26.2% of the 80 ProgramBench runs passing at least 90% of official tests. These are scanner findings, not validated vulnerability rates. Excluding three advisory-heavy classes reduces the latter rate to 6.2%. Same-task runs differ in their measured scores, while one reconstructed ProgramBench run exposes persistent findings from its first implementation write. A repair case study reduces the scanner signal while preserving tested behavior, but also reveals sensitivity to equivalent API rewrites. SDLI offers a way to study progress and security findings together. Its value for steering
agents and confirming exploitable vulnerabilities remains to be established.
Read the full abstract ▾
All authors Prateek Kumar Rajput, Abdoul Kader Kabore, Yewei Song, Melissa Tessa, Tailia Malloy, Jacques Klein, Tegawendé F. Bissyandé
Human-Computer Interaction
Alignment Games: A Framework for Conceptual Repair in Human-AI Collaboration
Hari Subramonyam, Maneesh Agrawala and Sean Follmer
The meaning of a concept in use is shaped by the situation, task, goals, and prior knowledge. For example, a request to make a poster "visually appealing for a five-year-old" might evoke bright colors and cartoon imagery for one collaborator, but less text, bold shapes, and visual simplicity for another. We call such task-relevant differences conceptual misalignment. We introduce
Alignment Games, a framework for making these differences visible and repairable during human-AI interaction. Drawing on theories of situated conceptualization, we characterize task-specific conceptual frames in terms of relevant attributes, values, relations, constraints, and priorities. We then define
alignment moves that intervene on the situation, the
reasoning used to interpret it, or the resulting frame. Through examples from educational content generation, creative coding, and argumentative writing, we show how these moves can be composed into repair sequences and derive design principles for supporting task-sufficient conceptual
alignment at runtime.
Read the full abstract ▾
Numerical Analysis
GAC-PINN: Geometry-Adaptive and Constraint-Enhanced Physics-Informed Neural Networks
Yanxin Zhang, Yong Zhang and Houbiao Li
For systems with steep gradients, sharp interfaces, or severe spatio-temporal coupling, Physics-informed neural networks (PINNs) suffer from spectral bias,
geometric inflexibility, and boundary constraint conflicts, which undermine accuracy and convergence. To overcome these issues, we propose a geometry-adaptive and constraint-enhanced PINN (GAC-PINN). The framework comprises four components: a gradient-driven adaptive grid mapping (AGM) for diffeomorphic point concentration with Jacobian regularization, an adaptive bandwidth hard-constraint ansatz with spatially-varying boundary transition widths, a Gaussian
Fourier feature mapping as a spectral preconditioner to further enhance high-wavenumber representation, and an operator-aware router that automatically selects the appropriate hard-constraint construction based on whether the governing PDE contains temporal derivatives. An AGM callback mechanism and a three-stage training strategy ensure stable coordination.
Benchmarks including the viscous Burgers equation, a sharp-peaked 2D Poisson problem, and the Allen-Cahn phase-transition equation show that GAC-PINN attains relative (L^2) errors of ((1.747\pm 0.450)\times 10^{-4}), ((2.868\pm 0.947)\times 10^{-5}), and ((1.756 \pm 0.712)\times 10^{-3}), respectively, consistently outperforming the baselines. Ablation studies further reveal that AGM alone yields a substantially lower error than residual-based adaptive refinement (RAR), while RAR becomes beneficial only when combined with FFM, demonstrating a context-dependent module interaction. Convergence analysis verifies rapid error reduction and saturation with increasing resolution, establishing a practical adaptive framework for high-fidelity simulation of problems with localized sharp features in applied mechanics and computational physics.
Read the full abstract ▾
Computer Vision
CarveMix-RC: Addressing Rare-Class Imbalance Through Lesion-Aware Synthetic Augmentation for Brain Metastasis Segmentation
Md Shibly Sadique, Md Fayaz Bin Hossen, Michael L. Evans et al. (+4 more)
Accurate
segmentation of post-treatment
brain metastases is essential for treatment planning, longitudinal disease monitoring, and quantitative assessment of therapeutic response. The BraTS-MET 2026 Task 1 challenge introduces a clinically relevant
segmentation problem involving four anatomically distinct tumor subregions: non-enhancing tumor core (NETC), surrounding non-enhancing FLAIR hyperintensity (SNFH), enhancing tumor (ET), and the resection cavity (RC). Among these, RC
segmentation is particularly challenging because of its low prevalence, heterogeneous postoperative appearance, and lesion-wise evaluation protocol, leading conventional
segmentation networks to prioritize dominant tumor classes during optimization. The proposed nnU-Net-based framework explicitly addresses RC
segmentation through four complementary components: (i) RC-weighted Dice and Cross-
Entropy optimization to alleviate class imbalance, (ii) anatomically consistent cavity augmentation to increase the diversity of postoperative cavity appearances, (iii) a residual encoder architecture for enhanced multi-scale feature learning, and (iv) lesion-aware morphological post-processing to suppress false-positive cavity predictions while preserving anatomically plausible structures. The framework is evaluated on the BraTS-MET 2026 Task 1 online validation
benchmark. Among the evaluated configurations, the ensemble model (Residual Encoder nnU-Net + nnU-Net + RC-aware CarveMix) achieves the best performance, with lesion-wise Dice scores of 0.732, 0.752, 0.708, and 0.575 and corresponding NSD scores of 0.794, 0.798, 0.727, and 0.474 for ET, TC, WT, and RC, respectively. These experimental results show that integrating RC-aware optimization, anatomically consistent augmentation, and lesion-aware post-processing provides an effective strategy for improving rare resection cavity
segmentation in post-treatment
brain metastases.
Read the full abstract ▾
All authors Md Shibly Sadique, Md Fayaz Bin Hossen, Michael L. Evans, Walia Farzana, Asfaqur Rahman, Ahmed Temtam, Khan M. Iftekharuddin
Machine Learning
ConRAG: Lightweight inference of multi-hop relations
Kilian Bänziger, Sonia Laguna, Markus Kreft et al. (+4 more)
Understanding how two entities are connected often requires tracing multi-hop relations across documents to identify intermediate entities and supporting evidence that explain a connection. This is a task that appears frequently in scientific research and other knowledge-intensive analyses. We formalise this setting as multi-hop relation inference: given two known endpoint entities, we aim to recover the bridge entities and evidence-grounded
reasoning chains that connect them across a document corpus, and to generate an explanation grounded in the retrieved evidence. Existing multi-hop RAG systems typically seek an unknown answer entity rather than explicitly recovering the connection between two known endpoints and graph-based approaches often rely on costly LLM-extracted knowledge graphs that limit scalability to large document collections. We introduce ConRAG, which builds a lightweight entity-document graph from entity co-occurrence and LLM-based entity filtering. Its connective
retrieval infers and semantically ranks paths between two endpoints. On MuSiQue and 2WikiMultiHopQA, ConRAG consistently improves bridge entity and
reasoning chain recovery over strong RAG baselines, while reducing graph-indexing
token cost by up to roughly 1.5 orders of magnitude. Our results show that endpoint-constrained path
retrieval provides an effective and index-efficient approach to evidence-grounded relation discovery.
Read the full abstract ▾
All authors Kilian Bänziger, Sonia Laguna, Markus Kreft, Robert Jakob, Kevin O'Sullivan, Lasse B. Strand, Julia E. Vogt
Game Theory
Envy-Free Decompositions of Random Assignments: Settling Four Agents, and What Lies Beyond
Keyi Li, Yihao He and Quanyi Li
A random assignment of n indivisible objects to n
agents is specified by its assignment
matrix and implemented by drawing a deterministic assignment from a Birkhoff-von Neumann decomposition. Kawase et al. observed that the choice of decomposition matters for
fairness: a
matrix that is envy-free in the sense of
stochastic dominance (SD-EF) can be decomposed so that some
agent envies another with probability close to 1. They call a decomposition Dec-EF if every
agent envies every other
agent with probability at most 1/2, proved that every SD-EF
matrix admits a Dec-EF decomposition when n <= 3 or when there are at most two distinct preferences, and left the general case open. We settle the first open case: every SD-EF
matrix with four
agents admits a Dec-EF decomposition. The worst case over the SD-EF polytope of a profile is attained at a vertex, and our computer-aided proof enumerates all 26,927 vertices for the 762 profiles up to
symmetry in exact arithmetic and certifies each by a rational decomposition. The same method settles five
agents with at most four distinct preferences and the probabilistic serial rule for all five-
agent profiles, and
adversarial search up to seven
agents finds no counterexample. For general n, an envy-budget identity shows that 1/2 is the best possible threshold. We prove that every SD-EF
matrix with at most two distinct rows admits a Dec-EF decomposition, and that the maximum-
entropy decomposition is Dec-EF whenever all
agents but two share a preference; the latter proof rests on a new monotonicity lemma for weighted least-squares rankings. In general, natural decompositions fail: greedy Birkhoff-von Neumann can come arbitrarily close to envy probability (n-1)/n, and maximum
entropy fails at n = 4 when all preferences differ. Deciding whether an arbitrary random assignment, not necessarily SD-EF, admits a Dec-EF decomposition is strongly NP-complete.
Read the full abstract ▾
Computer Vision
G$^3$-LoRA: Organizing Reward-Weighted Video Data with Gradient-Guided Grouped LoRA
Jia Song, Wenhow Li, Lichen Bai et al. (+2 more)
Post-training foundation
video models on heterogeneous reward-weighted data usually assume that all data categories induce compatible updates. This assumption is fragile when categories correspond to different skills, domains, or evaluation dimensions. We study this problem in text-to-
video post-training, where VBench2.0 dimensions define data buckets and an external
multimodal reward pipeline assigns sample weights. We propose G$^3$-LoRA (Gradient-Guided Grouped LoRA), a data organization procedure that probes category-level gradients induced by reward-weighted
video samples, removes the shared global update direction, clusters categories by residual gradient compatibility, trains group-specific LoRA experts, and consolidates them into one adapter by weight merging followed by on-policy
distillation from the experts. We motivate this procedure by viewing reward-weighted flow matching as velocity-field regression: incompatible reward dimensions may prefer different denoising directions in overlapping noisy latent regions, causing shared LoRA training to average capabilities. On Wan2.1-T2V-1.3B-Diffusers, the merged grouped adapter improves the matched VBench2.0 evaluation over the base model, a joint reward-weighted LoRA baseline, and random, semantic, and raw-gradient partitions trained with the same pipeline; an independent evaluator agrees, and on CogVideoX-2B grouping avoids the negative transfer of joint training. The gain is not uniform: merging compresses the largest specialist gains,
distillation recovers part of this loss, and camera motion and several local-quality dimensions remain challenging. Together, these results suggest that gradient compatibility can serve as a practical diagnostic for organizing reward-weighted
video post-training data.
Read the full abstract ▾
All authors Jia Song, Wenhow Li, Lichen Bai, Bada Ye, Zeke Xie
Artificial Intelligence
Beneath the Tokens: A Performance Engineering Study of Multi-Token Prediction in GPU-Accelerated LLM Inference
Suwesh Prasad Sah
Autoregressive large
language model inference repeatedly invokes the target model to generate one
token at a time, making generation sensitive to GPU
memory movement and sequential execution. This study evaluates two-
token multi-
token prediction (MTP) against autoregressive decoding in a controlled single-request deployment on an NVIDIA A10G GPU. A 360-request
benchmark covered plain-text,
reasoning-intensive, and tool-calling workloads, while runtime telemetry, Nsight Systems, PyTorch Profiler, and selected Nsight Compute measurements were used to explain the observed performance. MTP increased output throughput by \(1.91\times\) to \(2.19\times\) across all
prompts and reduced time to first output by 10.0–14.2%. Median mean acceptance length ranged from 2.370 to 2.595
tokens per verification iteration. Profiling showed that MTP introduced a longer and more complex execution path, including proposal, sampling,
attention, gathering, and reduction operations. However, it required 56.4–78.1% fewer executions of the selected repeating CUDA Graph per generated
token. The dominant MTP GEMM kernel was not faster than the dominant autoregressive GEMV kernel, and selected instances of both approached the A10G
memory-bandwidth limit. These results show that MTP improved inference through amortization: greater
token progress reduced repeated GPU execution sufficiently to outweigh the additional speculative-execution cost.
Read the full abstract ▾
Discrete Mathematics · Cross-listed from math.CO
Fractional Dichromatic Number and Domination in Tournaments
Paul Colinot and Alantha Newman
Bourneuf, Charbit and Thomassé [BCT25] showed that the domination number of a tournament can be bounded as a function of its fractional dichromatic number. The function proved was exponential and the tools were based on VC-dimension. In this paper, we present two new proofs of this
theorem. The first proof is based on a reduction to the problem of bounding the domination number of a $(1/2-\epsilon)$-majority tournament, for which [BCT25] and Charikar, Ramakrishnan and Wang [CRW26] gave tight bounds. This proof yields the same exponential bound on the domination number as in [BCT25]. The second proof gives a quasilinear bound for the domination in terms of the fractional dichromatic number. It was obtained via AI and was inspired by the recent book proof of the existence of a Condorcet Winning Set of size five due to Ramakrishnan [Ram26].
Read the full abstract ▾
Artificial Intelligence
5W1H+Which: Context-Valid Semantic Indexing with Progressive Ontology Binding
Yaxiao Liu, Pengbo Liu, Yiwen Liu et al. (+2 more)
Semantic indexing must preserve reusable source information without committing too early to one business schema, while providing checkable premises for
reasoning. We propose 5W1H+Which, a design that separates source-grounded content extraction from progressive ontology binding. The 5W1H questions organize independently addressable content units; Which records links to versioned ontology elements, mapping relations, applicability scopes, and validation states. Time, location, system environment, and participant roles constrain when facts, bindings, and rules may be used. Unbound content remains searchable, whereas formal
reasoning requires explicit premise checks. The design distinguishes business valid time, system knowledge time, and operational traces, and tracks dependencies for revalidation and incremental maintenance. Worked examples illustrate cloud migration and temporal policy validity. The resulting linked corpus can support downstream training and evaluation organized around
benchmarks, positive and negative examples, trajectories, and costs. Trajectories preserve steps, evidence-backed checkpoints, recovery, and local-to-global failure impact; reusable skills remain downstream abstractions requiring cross-episode validation. We specify falsifiable hypotheses and capability-matched baselines to test cross-task evidence coverage, contextual misuse, and update cost under equal information and budgets. The contribution is a proposed indexing and maintenance contract, not a new universal ontology or post-training
algorithm. No experiments have yet been conducted, and no performance improvement is claimed.
Read the full abstract ▾
All authors Yaxiao Liu, Pengbo Liu, Yiwen Liu, Yihua Guan, Jiaxing Song
Software Engineering
Research-Native by Construction: Minimal Nodes, Re-verifiable Workflows, and Compounding Memory for Long-Horizon Scientific Agents
Di Wang, Yu Liu, Bing Cui et al. (+5 more)
We describe AfS (
Agent for Science), a platform built for long-horizon scientific work, where a project runs for tens of hours across dozens of
agent runs with a human present only occasionally. Most
agents for science are general coding
agents with a skills folder attached, and they inherit that lineage's failure mode: under pressure to finish, they fabricate, skip, or smooth over. Our design rests on one claim: most of the credibility of machine-made research can be moved from asking the model to behave to making the non-compliant state unrepresentable. We encode research discipline as mechanically enforced laws (commitment before measurement; unforgeable freezing; reports are not facts; evidence persists but verdicts do not; negative results are first-class; mechanical questions to the framework and semantic judgment to the model), organized around three time horizons: a minimal set of research nodes within a run, an inquiry contract with frozen closure conditions and a hash-chained artifact ledger within a project, and a two-tier knowledge base with promotion by rewriting across projects. This is a system description written under one rule: each mechanism appears in exactly one place, with the invariant it enforces, the failure it prevents, the way it is realized, and the cost it imposes. It covers the node contract, the write-path gates, the two-tier
memory, and the runtime substrate. Three traces walk real failure attempts through the mechanisms that catch them, and two closed campaigns are included as worked illustrations rather than as an evaluation. We report no
benchmark: a process-integrity suite that would support quantitative comparison is under construction, and what we can measure today is only the operating cost of the machinery.
Read the full abstract ▾
All authors Di Wang, Yu Liu, Bing Cui, Chaoqun Ji, Dongyuan Ni, Jingyu Lu, Kunlei Cui, Pu Qin
Machine Learning
Subgroup Rank-1 Lattice for Practical High-dimensional Black-box Integral Approximation
Yueming Lyu
Estimating integrals of black-box, high-dimensional functions, from expectations and kernel mean
embeddings to the softmax kernel in self-
attention, is a basic subroutine in machine learning. Rank-1
lattice rules suit this setting: they query the integrand only at a fixed point set and need no gradients. When the $n$ points serve as a design
matrix $X\in\mathbb{R}^{n\times d}$ for a feature map, however, computing $\Psi(X)^\top v$ or $\Psi(X)w$ for an elementwise nonlinearity $\Psi$ costs $O(nd)$ time and
memory for any standard quasi-Monte Carlo point set. We study subgroup rank-1
lattices, whose Korobov generator $(1,t,\dots,t^{d-1})$ uses a scalar $t$ of fixed multiplicative order $m$. Splitting $\mathbb{F}_n^\times$ into cosets of $\langle t\rangle$ reduces both maps to short cyclic correlations evaluated by FFT, giving exact results for arbitrary $\Psi$ in $O(n\log m)$ time and $O(n)$
memory, without forming $X$. Since fixing $m$ falls outside classical component-by-component theory, we prove convergence directly: via resultants with the cyclotomic
polynomial $\Phi_m$, the squared worst-case error in the Korobov space decays as $O(n^{-(\alpha-1)/(m-1)})$ for
prime $m\ge d+1$, and this threshold is exact. Using the splitting of $n$ in $\mathbb{Q}(\zeta_m)$, averaging over the $m-1$ admissible generators improves the constant by a factor $\Theta(m-1)$. Empirically, the subgroup
lattice beats Gaussian and orthogonal random features and scrambled Sobol' and Halton points in 49 of 54 synthetic kernel-estimation settings and all 45 softmax-
attention settings on nine real
datasets, and builds a sample set with $d=2048$, $n\approx4.1\times10^7$ in 2.3 ms.
Read the full abstract ▾
Machine Learning
ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models
Robert Lampel, Timon Klein and Sebastian Sager
We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architecture at inference time. A network $N=N_2\circ N_1$ is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls $N_1(x)$ toward the prototype of its class with a classification loss of $N_2$ evaluated on samples drawn around the prototypes, whereat no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network $N_2\circ N_1$ is used. Across CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and
vision transformer backbones, lifted training improves test accuracy by up to five percentage points over variants without lifting under a shared tuning protocol. Moreover, we provide theoretical justification of those results.
Read the full abstract ▾
Networking
Edge-Assisted Multi-View Localization for Low-Altitude Economy under GPS-Challenged Environments
Zhengru Fang, Huanhuan Lou, Senkang Hu et al. (+5 more)
Unmanned aerial vehicles (
UAVs) serving the low-altitude economy require reliable localization in urban canyons, indoor facilities, and other GPS-challenged environments. Visual matching with a geo-tagged database provides an alternative source for absolute positioning, but onboard computation and energy limits motivate offloading the database and matching pipeline to an edge server. The resulting localization quality depends on what visual information can reach the edge in time under varying wireless-communication and edge-computing resources. In this paper, we propose a network-adaptive edge-assisted multi-view localization framework that combines scalable orthogonality-regularized variational information bottleneck (O-VIB) encoding, value-of-information (VOI)-guided request control, and value-aware edge scheduling. We design an O-VIB model that supports nested latent prefixes from 8 to 128 dimensions and four
UAV view modes. Each
UAV requests edge assistance when the predicted localization-risk reduction exceeds the communication and service costs. On CARLA multi-view
UAV data, VOI-guided control can lower the mean and 95th-percentile (p95) route errors by 24.8% and 31.0%, respectively, relative to budgeted periodic offloading under a matched per-route traffic budget. In indoor
UAV experiments with motion-capture ground truth, our design can lower the mean position error by 28.0% relative to uncompressed all-view CLIP
retrieval while cutting the descriptor traffic by 98.6%, using a 0.145 KB semantic representation. Under high congestion, a VOI-weighted scheduler with waiting-age and deadline shaping can lower the edge-side p95 latency of the top-10% high-value requests from 137.7 ms to 32.8 ms.
Read the full abstract ▾
All authors Zhengru Fang, Huanhuan Lou, Senkang Hu, Yihang Tao, Zongdian Li, Yiqin Deng, Jingjing Wang, Yuguang Fang
Distributed Computing
Analyzing Solana's Blocks and Transactions
Yaron Hay, Dvir David Biton and Roy Friedman
Solana is one of the most popular blockchains, and is arguably the most widely used blockchain for smart contracts, also known as dApps. Understanding the types of smart contracts that are being executed by Solana and their interplay is therefore highly beneficial both for designers of modern blockchains and developers of smart contracts. To that end, in this paper we analyze a million recent Solana blocks. We report statistics about the size of blocks (number of transactions per block), execution time units for individual transactions and fees, and invoked Solana programs. Further, based on the declared readset and writeset of each transaction, as mandated by Solana, we analyze the conflicts and corresponding conflict graphs arising within each block. These latter statistics are important to understand the potential for parallelism in the network, which is one of the main claimed benefits of Solana. The data and code are available in open source.
Read the full abstract ▾
Human-Computer Interaction
The Future of Visualization Dashboards in the Age of Generative AI
Vaishali Dhanoa, Duosi Dai, Gabriela Molina Léon et al. (+2 more)
Generative AI promises easier dashboard creation, raising questions about the future of dashboards and the people who create and use them. We interviewed 16 experts based in 14 countries about their practices and expectations. Almost all expected dashboards to persist for recurring questions, monitoring, and reporting. They anticipated adaptive views and combinations of
language, graphical controls, and gestures, while emphasizing interaction as part of human exploration and understanding. Participants expected authors' responsibilities to shift toward specifying requirements, curating generated work, and evaluating outputs, with design knowledge and communication remaining important. Easier creation also raised concerns about validation effort, users' understanding, maintenance, and personalization weakening shared understanding. We discuss seven opportunities for research and practice concerning validation, end-user education, dashboard proliferation and rot, organizational guidance, adaptation, novel visualizations, and accountability for AI-generated content. Our findings connect dashboard
evolution with the human and organizational work needed to sustain their use.
Read the full abstract ▾
All authors Vaishali Dhanoa, Duosi Dai, Gabriela Molina Léon, Eduard Gröller, Niklas Elmqvist
Machine Learning
QAM: Quadratic-Accurate Checkpoint Merging via Sequential Consistency
Shihao Wang, Rui Kong, Xinran Chen et al. (+7 more)
Saved checkpoints record states along a training trajectory, but generally do not determine the updates at states that would be visited under a different schedule. We study how accurately these checkpoints can reconstruct the endpoint of a sequential reference with prescribed update strengths. Under a common local transition model, two checkpoint-index moment conditions characterize all convex merges that agree with this reference through second order. We then prove an information limit that for nondegenerate profiles, no
algorithm using only a fixed-length gradient-descent (GD) history with step size $h$ can achieve $o(h^3)$ endpoint error uniformly over a fixed class of smooth, strongly convex losses. The lower bound follows from two losses with identical GD checkpoint histories but sequential reference endpoints separated by $\Omega(h^3)$. Quadratic-Accurate Merging (QAM) achieves a matching uniform $O(h^3)$ endpoint error bound. Its explicit coefficients also define the unique profile-dependent merge that exactly matches the sequential GD reference across all fixed quadratic objectives. Across two public Adam checkpoint trajectories (SmolLM3-3B and OpenEuroLLM-Prelude-9B), three windows and three profiles per model, and 15 tasks, QAM shows mixed results for short windows and broader advantages over Warmup-Stable and Merge (WSM) for longer windows. Matched-moment GSM8K diagnostics further show that local consistency alone does not fully determine downstream scores. These results characterize the reconstruction limits of saved histories, provide a coefficient rule that attains the optimal rate, and assess its practical utility.
Read the full abstract ▾
All authors Shihao Wang, Rui Kong, Xinran Chen, Hui Wu, Qipeng Qian, Jinman Zhao, Jiashu Zhao, Yuchen Li, Jimmy Huang, Dawei Yin
Machine Learning
EdgeCraft: Automated Model Crafting for Edge IoT
Genglin Wang, Kaiwei Liu, Liekang Zeng et al. (+4 more)
Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific scenario requires navigating a huge search space spanning data representation, model design, training on domain-specific data, and runtime customization. This workflow is fragmented and difficult to scale across diverse edge applications. We present EdgeCraft, an LLM-driven system that turns high-level intent into deployable edge ML artifacts. Building such a system raises two challenges: (1) How can an LLM be guided to find high-quality solutions that meet dynamic SLOs for task quality, latency, and energy? (2) How can trustworthy target-device verification be obtained at low cost? EdgeCraft addresses these challenges with two designs. (1) A constraint-aware synthesis tree explores alternative candidates and uses measured SLO gaps to guide each improvement. (2) A multi-fidelity verifier progressively combines low-cost checks with full target-device verification to reduce verification cost while preserving reliable verification results. It also records verified failures for reuse, avoiding repeated device work. To support concurrency, EdgeCraft provides a multi-tenant runtime that runs cloud training and target-device verification in parallel while isolating requests. Across 50 public tasks, EdgeCraft exceeds the task-specific Reference in best-observed quality on 40 tasks and finds an SLO-feasible artifact on 45, with the two outcomes overlapping on 38 tasks. Moreover, EdgeCraft achieves competitive performance on our self-collected SEN
dataset, suggesting its generalizability to real-world IoT sensing tasks.
Read the full abstract ▾
All authors Genglin Wang, Kaiwei Liu, Liekang Zeng, Wangsong Yin, Shangcheng Jin, Guoliang Xing, Zhenyu Yan
Machine Learning
Learning to Re-Draft: A Variational Stackelberg Game for Discrete Diffusion
Dmitrii Moor, Federico Tomasi, Paul N. Bennett et al. (+2 more)
Discrete
diffusion models offer the ability to re-draft, revisiting and correcting earlier
tokens throughout generation. This capability depends on the forward corruption process that defines what the denoiser learns to correct. Masked
diffusion models fix
tokens once they are unmasked, while uniform
diffusion permits revisions but relies on uniformly random
token substitutions. We instead learn which substitutions are most useful for training the denoiser to re-draft. We introduce Variational Stackelberg Discrete
Diffusion (VSDD), a framework for learning a semantically aware corruption process. VSDD formulates training as a leader-follower game: the leader defines a Markovian corruption process parameterized by the denoiser's
token embeddings, while the follower optimizes a variational denoising objective with the corruption process held fixed. The leader rewards corruptions based on how much the denoiser improves after learning from them, rather than on how easily the current denoiser can reconstruct them. We measure this improvement under a fixed reference corruption process, approximate the follower's response with a one-step gradient update, and optimize the leader using a score-function
estimator. We evaluate VSDD across molecular, text, and playlist generation. VSDD substantially improves molecular validity over uniform and masked
diffusion, reduces text perplexity relative to uniform
diffusion while remaining competitive with masked
diffusion, and achieves sizable improvements in offline playlist recommendation metrics.
Read the full abstract ▾
All authors Dmitrii Moor, Federico Tomasi, Paul N. Bennett, Alice Wang, Mounia Lalmas