Game Theory
Weighted Fair Division of Indivisible Mixed Manna
Nicholas Teh
We study weighted fair division of indivisible mixed manna under additive valuations. First, we resolve the general existence open question for weighted envy-freeness up to one item (WEF1), and show that every instance with arbitrary positive entitlements admits a complete WEF1 allocation computable in
polynomial time. We then show that existence does not imply any welfare guarantee, i.e., the utilitarian price of WEF1 is infinite, even for two unweighted
agents with normalized valuations, common item signs, and singleton values in a fixed four-value set; a welfare-maximizing WEF1 allocation in the construction is fractionally Pareto optimal. Second, suppose each
agent $i$ has a number $a_i>0$ such that their valuation for any item is $-a_i$, $0$, or $a_i$. Then, for arbitrary entitlements, a weighted maximin share (WMMS) allocation always exists, is computable in
polynomial time, and can be chosen to be fractionally Pareto optimal. An exact formula for each WMMS value leads to a
polynomial-time flow
algorithm. In this class, every WEF1 allocation satisfies a best possible additive WMMS guarantee whose loss depends on the
agent's entitlement relative to the largest entitlement. Thus maximum entitlement
agents receive exact WMMS and, under equal entitlements, every WEF1 allocation is also MMS-fair. Allowing a second positive magnitude can violate exact WMMS, while unrestricted entitlement ratios rule out any fixed multiplicative WMMS guarantee compatible with WEF1 for chores.
Read the full abstract ▾
Robotics
SG-AMP: Scene-Graph-Guided Active Perception and Semantics-Aware Motion Planning for Pepper Plants
Rohit Menon, Shiva Rudra Lolla, Niklas Mueller-Goldingen et al. (+3 more)
We present SG-AMP, integrating robust depth completion with input-conditioned uncertainty, persistent panoptic mapping, plant scene-graph
reasoning, and semantics-aware active view-motion planning. Beyond inspecting uncertain observed regions, the scene graph explicitly hypothesizes unobserved pepper–peduncle attachments and directs close-range sensing toward them. Candidate views are selected according to expected information gain, while class-dependent motion costs distinguish protected peppers, peduncles, and stems from conditionally traversable foliage. On pepper data, the perception network achieves $55.27\%$ semantic mIoU, $38.67\%$ PQ, and $40.62\,\mathrm{mm}$ depth RMSE, while input-conditioned uncertainty improves NYUv2 NLL from $-1.6518$ to $-1.6925$ and AUSE from $0.0102$ to $0.0087$.
Read the full abstract ▾
All authors Rohit Menon, Shiva Rudra Lolla, Niklas Mueller-Goldingen, Gokul Chenchani, Ribana Roscher, Maren Bennewitz
Numerical Analysis
Greedy sampling designs via reduced basis methods: optimal recovery in the uniform norm
Sebastian Neumayer, Kateryna Pozharska and Tino Ullrich
We study optimal sampling recovery in reproducing kernel
Hilbert spaces (RKHS) in the uniform norm. For every RKHS with bounded kernel, we establish new comparisons between linear sampling widths and Gelfand widths that overcome the known square-root gap, without requiring a measure or a Christoffel-type condition. Our bounds rely on nested sampling designs obtained by kernel interpolation at (weak) P-greedy points. Under additional (
polynomial) decay assumptions the decay rate of the Gelfand widths directly transfers to the sampling widths. With either a logarithmic oversampling or passing to the square root of the Gelfand widths we obtain a direct comparison (requiring no decay assumption) between them. This is particularly effective for super-
polynomial decay, such as in Paley-Wiener spaces. Our results follow from representations of both widths in terms of kernel translates and yield, in the opposite direction, a new existence result for a sharp reduced basis selection. Numerical experiments for Legendre, mixed-Sobolev, and Paley-Wiener kernels illustrate our findings.
Read the full abstract ▾
Computation and Language
Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics
Maksim Evdokimov, Matvey Ivanov, Dmitrii Tsiupin et al. (+3 more)
Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a fraction of workflows,
privacy rules preclude external models, and existing open-source VLMs that clear quality thresholds cost more to serve than human annotation. We present a deployed document-understanding system built on a Mixture-of-Experts VLM (35B total, 3B active), fine-tuned on in-house production data mixed with open-domain documents curated by a Difficulty-Aware pipeline for layout diversity, fact-extractability, and cross-model consistency. Fitting on a single H100 and serving heterogeneous workflows via prompting, the model leads all deployable (non-
reasoning) baselines up to an order of magnitude larger. A quality-adjusted cost analysis, with confirmation and correction costs calibrated from production telemetry, shows it reduces expected costs by over 80% against the human baseline and by more than 50% against the best competing open-source model, while larger baselines remain economically unviable.
Read the full abstract ▾
All authors Maksim Evdokimov, Matvey Ivanov, Dmitrii Tsiupin, Olga Tsymboi, Anatolii Potapov, Aleksandr Ivanov
Computation and Language
Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs
Jingtan Wang, Arun Verma, Xiaoqiang Lin et al. (+4 more)
How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open problem. Existing work characterizes only broad trends (e.g., SFT dominates in low-data regimes), lacks a principled allocation framework, and does not examine whether the optimal ratio transfers across model sizes. We frame this problem in terms of near-optimality: rather than seeking a single optimal SFT-RL ratio, we characterize the near-optimal region, the set of allocations within a specified tolerance of peak performance. Empirically, this region is wide even for small tolerances (2-10%), widens with model scale, and transfers reliably from small proxy models to large target models. This yields a practical strategy: small proxy-model experiments suffice to identify a transferable near-optimal region, eliminating the need for exhaustive large-scale search. Our results hold consistently across tasks, model families, and both preference-based off-policy and reward-supervision on-policy RL methods. We further analyze how the asymmetry in annotation costs between SFT and RL data shifts the near-optimal region.
Read the full abstract ▾
All authors Jingtan Wang, Arun Verma, Xiaoqiang Lin, Zhengyuan Liu, Nancy F. Chen, Daniela Rus, Bryan Kian Hsiang Low
Computation and Language
From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
Olga Tsymboi, Dmitrii Stoianov, Ramil Latypov et al. (+11 more)
Data-residency constraints force enterprises to self-host LLMs, but continuous adoption of newer models without decommissioning their predecessors expands the serving fleet, fragmenting a finite GPU pool. We consolidate traffic from over 200 internal applications onto a single model by closing quality gaps identified through production error analysis along three axes: instruction following, function-calling, and internal task distribution. Quality is tracked by offline
benchmarks stratified to production traffic and scored by deterministic verifiers or calibrated LLM judges. Rather than optimising all objectives jointly, which introduces cross-domain reward interference, we train a separate GRPO expert per axis and merge them via two-stage SLERP. Each expert's reward exposes a distinct failure mode, namely semantic collapse, over-calling, and verbosity hacking, each requiring a domain-specific fix. In non-
reasoning mode the recipe surpasses a ${\sim}7\times$ larger by total parameters baseline on the in-house Arena with 69.6 to 65.8, instruction following with 0.85 to 0.83, and function-calling with 0.79 to 0.77, while lifting general dialogue
benchmarks. The model absorbs 50% of platform traffic, 116M requests per month, at a fraction of the serving cost.
Read the full abstract ▾
All authors Olga Tsymboi, Dmitrii Stoianov, Ramil Latypov, Danil Taranets, Daniil Dryabin, Mikhail Gashkov, Viktor Zelenkovskiy, Aleksandr Fida, Gleb Alektorov, Nikita Gulyakov, Arthur Babkin, Aleksandr Medvedev, Pavel Gein, Anatolii Potapov
Systems and Control
Stability of Droop-Controlled Low-Frequency Transmission Lines
Rafael Castillo-Sierra, Giri Venkataramanan and Dionisio Ramirez
Low-Frequency AC (LFAC) transmission systems employing power converters are being considered for a varity of applications. This work studies the small-signal stability of an LFAC transmission line controlled by the Droop Control Strategy.
Eigenvalue Analysis is used to determine how the controller droop gains, operating frequency, transmission line parameters, and the operating point affect system stability. The results show that the overall system's dynamic is governed by the sum of the droop gains of the AC/AC converters. Analytical results that give insights on how the different system's parameters affect the critical stability point are presented. The results indicate that system stability is affected by the line's length, the line's R/X ratio, operating frequency and voltage.
Read the full abstract ▾
Human-Computer Interaction
Evaluating Usability in Biomedical Visualization: Rethinking Heuristic Evaluation for Spatial Omics and Multidisciplinary Research Platforms
Yulia A. Levites Strekalova, Rachel Liu Galvin, Jessica M. Ray et al. (+11 more)
Introduction: Clinical research informatics (CRI) platforms support biomedical discovery by integrating advanced computational tools into research workflows. Emerging technologies such as spatial omics and AI-enabled imaging expand research capabilities but introduce complex interfaces that increase cognitive burden and alter established analytical processes. Traditional usability frameworks identify general usability issues but often miss challenges specific to high-dimensional biomedical data. Methods: We conducted two complementary studies involving 39 participants to evaluate conventional usability heuristics and identify CRI-specific criteria. Study 1 included 19 undergraduates completing interactive tasks, and Study 2 involved 20 clinical professionals completing an asynchronous hierarchical task framework. Observational and interview data were analyzed using deductive coding based on standard usability heuristics and emerging CRI-specific themes. Results: Simultaneous presentation of complex data overlays and analytical tools overwhelmed users, particularly those with limited spatial-omics experience. Participants relied on trial-and-error exploration and struggled with unlabeled tools in data-rich environments. Feedback indicated that users benefit from phased onboarding, contextual guidance, and progressive feature introduction rather than immediate access to all functionality. Discussion: High-dimensional research platforms require domain-specific usability criteria beyond traditional frameworks. We propose three specialized heuristics: Active Parameter Transparency, Point-of-Use Guidance, and Phased Feature Disclosure. These heuristics help developers manage complexity, provide contextual support, and improve accessibility for multidisciplinary research teams.
Read the full abstract ▾
All authors Yulia A. Levites Strekalova, Rachel Liu Galvin, Jessica M. Ray, Samuel P. Border, Mishal Khan, Samantha Hoffman, Christina D. Beharry, Katie Kloss, Philipp Haessner, David Manthey, Sanjay Jain, Michael T. Eadon, Laura Barisoni, Pinaki Sarder
Artificial Intelligence
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Teachers
Giovanni Bonetta, Matteo Merler, Davide Zago et al. (+2 more)
Vision-
Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they must be queried at every step, do not improve from environment interaction, and can repeat systematic errors. We study how to learn a cheap autonomous policy from an online, expensive, and imperfect but informative VLM teacher. We propose SAGE (Selective
Agent Guidance via
Entropy), a framework that queries a VLM only when the learner is uncertain, executes the suggested action during training, and distills guidance into a lightweight Reinforcement Learning (RL) policy. Because VLM advice is not always reliable, SAGE can weight teacher-action
distillation using environment-derived advantages rather than treating all suggestions as equally useful. Across sparse-reward visual
reasoning and
navigation tasks, SAGE learns policies that act without VLM guidance at evaluation time and improves over unguided RL in several environments, including settings where the learned policy exceeds its VLM teacher. The results show that selective guidance is most beneficial when the VLM can help the
agent discover high-reward trajectories, and less useful when unguided exploration already succeeds or teacher actions do not lead to informative experience. SAGE also reduces VLM usage by prompting the teacher only on a fraction of training steps and requiring no VLM calls at deployment. Overall, our results suggest that VLMs don't need to be used as fixed policies to be useful; they can instead act as temporary, imperfect sources of guidance whose value is tested and internalized through interaction.
Read the full abstract ▾
All authors Giovanni Bonetta, Matteo Merler, Davide Zago, Rossella Cancelliere, Bernardo Magnini
Computation and Language
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Classification
Manish Gupta, Chaitanya Giri and Jayasimha Talur
Large
language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large label spaces, a common approach retrieves top-$K$ candidate labels by
embedding similarity and
prompt the LLM to choose among them. However, top-$K$
retrieval reduces the number of candidates but does not help the model tell similar ones apart. When two similar labels both appear as candidates, the model lacks the signal to choose correctly between them. We propose a framework that (1) identifies which label pairs the model struggles to distinguish, (2) expands the candidate set to include confusable labels, and (3) generates targeted rules to differentiate between similar candidates. The framework requires no fine-tuning, and the generated rules transfer to smaller, cheaper models. On three
benchmarks (WOS, Flipkart, LEDGAR), our approach improves Macro F1 by up to 10.0pp over
retrieval baselines, with smaller models (2B–20B) gaining up to 11.5pp via cross-model transfer.
Read the full abstract ▾
Computation and Language
A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains
Ema Salkić, Alexander Fichtl, Philipp Ulrich et al. (+3 more)
Semiconductor supply chains face escalating risks from geopolitical tensions, geographic concentration, and rapid technological shifts, yet no scalable system continuously extracts, structures, and prioritizes risk intelligence from public corporate disclosures. We present an end-to-end pipeline that retrieves corporate documents for
semiconductor companies and uses large
language models (LLMs) to extract the risks and opportunities they describe. It organizes these into a knowledge graph linking each item to its category, sources, and related events, then merges duplicates and ranks them with a three-layer mechanism combining an algorithmic formula, an LLM relevance adjustment, and expert validation. Applied to five companies across the value chain, the pipeline produces 76,207 scored items, of which an independent check finds 92.6% valid. The automated rankings match expert judgment at an average Spearman correlation of 0.55 for risks and 0.72 for opportunities, and the resulting
matrices identify trade restrictions as the dominant cross-company risk.
Read the full abstract ▾
All authors Ema Salkić, Alexander Fichtl, Philipp Ulrich, Hans Ehm, Marta Bonik, Georg Groh
Computer Vision
H3-World: Turning Language Understanding into World Control
Danze Chen, Zeqing Wang, Ziyue Lin et al. (+2 more)
We present H3-World, an efficient framework that turns the 33B MiniMax-H3
video generator into an interactive world model. Our key finding is that, as large
video generators become more capable,
language is emerging as a natural interface for control. MiniMax-H3, for example, already supports zero-shot control of character behavior and camera motion through natural-
language instructions. Building on this, H3-World turns this coarse
language interface into precise, temporally grounded world control, without introducing dedicated action modules. Specifically, we represent each action as a structured combination of character and camera instructions, and align them with the corresponding temporal
video latents. To make the control temporally precise, we further introduce temporal
attention routing, which restricts each instruction to its intended time interval and reduces control leakage across actions. Importantly, H3-World directly reuses the semantic representations learned during large-scale
video pretraining and requires only lightweight adaptation. With only 8,000 gameplay samples, 10,000 LoRA optimization steps, and 0.199% trainable parameters, H3-World achieves effective character and camera control while preserving strong generation quality. It also generalizes to unseen scenarios. These results show that the control capabilities emerging in large
video generators can be efficiently transformed into interactive world control.
Read the full abstract ▾
All authors Danze Chen, Zeqing Wang, Ziyue Lin, Xingyi Yang, Yeying Jin
Machine Learning
Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks
Jing Xiao, Xinhai Chen, Qinglin Wang et al. (+5 more)
Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructing directions from loss-specific gradients to reduce conflict before optimizer transformation. However, even when the constructed direction is conflict-free, this property may not be preserved after optimizer transformation. Let $a_t$ denote the direction constructed by gradient surgery, $u_t$ the optimizer proposal, and $\mathcal{C}_t$ the conflict-free cone induced by the loss-specific gradients. We show that modern optimizers can transform $a_t$ through mechanisms such as historical state, adaptive scaling, preconditioning, or decoupled weight decay, so $a_t \in \mathcal{C}_t$ does not generally imply $u_t \in \mathcal{C}_t$. We refer to this optimizer-induced discrepancy in conflict-freeness between $a_t$ and $u_t$ as Gradient-Update Mismatch (GUM). Accordingly, we propose Gradient-Update
Alignment (GUA), which projects $u_t$ onto $\mathcal{C}_t$ to obtain the aligned update $p_t$ and applies $p_t$ to the parameters. When the optimizer maintains internal state, GUA further adjusts this state toward targets reconstructed from the applied update. We conduct extensive experiments and find that GUM is widespread across momentum, adaptive, and
curvature-based optimizers, with conflict rates reaching up to 86.3%. Across all PINN settings, GUA achieves conflict-free applied updates and consistently improves various gradient surgery methods, reducing the relative $L_2$ error by up to 98.2% in individual settings. Data and code are available at https://github.com/JingXiao10/GUA.
Read the full abstract ▾
All authors Jing Xiao, Xinhai Chen, Qinglin Wang, Menghan Jia, Zhiquan Lai, Dongsheng Li, Jie Liu, Tiejun Li
Machine Learning
Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
Nabira Rashid and Manolis Kellis
We evaluate
embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domains under one protocol, competition mathematics (MathNet-Retrieve; 500 queries, 117,088-item corpus) and
embodied-
agent trajectories (ALFWorld-derived; 118 queries, 336 trajectories). In mathematics the failure is complete: strict Hit@1 at the heaviest disguise tier is 0.0% for both production embedders (bootstrap 95% CI [0.0, 0.0]) while the correct item sits in the top 10 nearly always, and in 95.2 to 99.8% of misses the winner is more lexically similar to the query than the correct answer. In trajectories, where surface variation is incidental, the same models land at or near hypergeometric chance when gold must involve a different object, and below chance for all three embedders once gold must differ in object and receptacle:
retrieval anchors on literal
tokens, not task structure. A lexical reranker control hurts in mathematics and helps in trajectories (closing 26 to 36% of the gap, CIs excluding zero); its sign reveals whether a
benchmark's surface variation is
adversarial or incidental. An LLM reranker recovers 5 to 63% of the gap in mathematics and 43 to 76% in trajectories; direction replicates across three judges (all 21
cells positive), but effect sizes, tier profiles, and the outlier judge change with domain (paired differences excluding zero everywhere). Mathematics gains concentrate on well-known competitions (+19.8 points, CI [+6.7, +33.2], one of six
cells), so part of the recovery is memorization. In a paired downstream experiment (210 queries, graders at 96 to 99% agreement), oracle
retrieval was indistinguishable from adversarially bad
retrieval (McNemar p = 0.678); the solver's 69.5% zero-shot accuracy is largely a truncation proxy (97 to 100% on finished answers), leaving no headroom.
Read the full abstract ▾
Computer Vision
BS: Take the Hint - Interactive Multitracer PET/CT Lesion Segmentation with a Scribble-Conditioned ResEnc U-Net
Marven Sherif, Amgad Elmasry, Youssef Ghazal et al. (+1 more)
Automated lesion
segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appearance of lesions across tracers. The autoPET/CT V challenge addresses this by making
segmentation interactive: user scribbles marking foreground and background are supplied alongside the image, and the
algorithm is expected to exploit them. We present our submission, a scribble-conditioned residual encoder U-Net operating on four input channels: CT, PET, and a sparse scribble map for each of foreground and background. The network is initialised from the autoPET-III winning weights and extended from two to four input channels, with the two scribble channels zero-initialised so that the pretrained representation is preserved exactly at initialisation. Every model is fine-tuned per fold from the corresponding autoPET-III fold checkpoint, so that no validation case is seen during pretraining. PET intensities are normalised against a per-scan aorta blood-pool reference derived from a CT
segmentation, which removes tracer- and centre-specific scaling without requiring lesion labels. At inference the five fold models are ensembled by averaging their softmax outputs per sliding-window patch, before Gaussian-weighted stitching. On the challenge's five-fold split, with each fold evaluated on its own validation cases, mean Dice is 0.554 and mean lesion-level F1 is 0.528 without scribbles, rising to 0.751 and 0.733 after five correction rounds. About 85% of that gain follows the first scribble, and the spread between fold models narrows five-fold over the same rounds, so interaction largely compensates for how well or badly a given model segments unaided.
Read the full abstract ▾
All authors Marven Sherif, Amgad Elmasry, Youssef Ghazal, Ayman Elghotni
Artificial Intelligence
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Yiming Huang, Ziche Liu, Junxia Cui et al. (+11 more)
Scientific law discovery has long been central to scientific progress, proceeding through iterative cycles of generating hypotheses, testing them against empirical evidence, and refining them under scientific constraints. As large
language models (LLMs) become increasingly involved in scientific research, whether they can discover scientific laws and how to evaluate this ability remain open questions. A central evaluation challenge is to move beyond familiar published equations while keeping discovery tasks grounded in scientific data and constraints. We introduce SciLaws-Bench, a curated collection of scientific task packages grounded in the source literature, each linking a scientific problem, supporting data, published reference equations, and scientific-validity rubrics. Through
agent-assisted curation and human verification, we assemble 118 problems spanning six disciplines, drawing on 381 papers, 291 candidate laws, and roughly 8M data points. Each problem supports two complementary evaluation settings. SciLaws-Real uses fixed scientific data to evaluate proposed laws for held-out predictive fit and scientific validity. SciLaws-Parallel evaluates recovery of a newly synthesized structural variant of a published equation through active queries to a simulator calibrated to the source data. Our evaluation reveals three limitations: good predictive fit need not imply scientific validity, recovering a published formula does not establish recovery of its new structural terms, and candidate selection remains a bottleneck in scientific law discovery. Project page: https://yiyihum.github.io/SciLaws-Bench
Read the full abstract ▾
All authors Yiming Huang, Ziche Liu, Junxia Cui, Zhuohang Wu, Yiqian Wang, Xinkai Zou, Lingjun Mao, Nan Huang, Naicheng Yu, Kaijie Zhu, Yue Ma, Kun Zhou, Letian Peng, Jingbo Shang
Computer Vision
What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models
Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan et al. (+3 more)
Self-supervised
video foundation models learn rich spatiotemporal representations, yet it remains unclear what visual concepts these representations encode, where they emerge across
transformer layers, and how they are geometrically organized. In this work, we tackle these three questions through a systematic layer-wise analysis of V-JEPA 2 and VideoMAE-v2. We leverage lightweight probes trained to discover three temporally grounded properties: (i) camera motion understanding, (ii) intuitive physics, and (iii) anomaly detection. Both models encode camera motion, with best results ($>90$ ROC AUC) emerging at 60-70% of network depth, and achieve moderate anomaly detection performance ($>60$ ROC AUC), but remain near chance on intuitive-physics tasks, suggesting a limited encoding of deeper physical
reasoning. Beyond classification, we find that temporal features from individual
videos form smooth low-dimensional trajectories in representation space, suggesting that camera motion is not only linearly decodable but also geometrically organized. Based on these results, we apply geometry-aware spline-based steering in the model's latent representations to interpolate camera motion, yielding steered
videos with smoother trajectories and more coherent temporal progression than linear interpolation.
Read the full abstract ▾
All authors Sharon S. Musa, Fereshteh Forghani, Harrish Thasarathan, Sonia Joseph, Matthew Kowal, Konstantinos G. Derpanis
Machine Learning
Linear Reusable Neural Bases Architecture for Network Compression
Binshuai Wang, Peng Wei and Mahyar Ghazanfari
Memory constraints remain a critical bottleneck in the deployment of large-scale AI models. Parameter sharing across network depth reduces model storage, but repeatedly applying an identical transformation limits flexibility across layers. Inspired by time–
memory trade-offs in classical
algorithms, we introduce the Linear Reusable Neural Bases (LRNB) architecture, an RNN-based framework that improves parameter efficiency through parameter reuse at the
neuron level. Each feedforward residual module is represented as a linear combination of shared neural bases, with depth-specific learnable coefficients and optional shifts providing flexibility across layers. This formulation reduces parameter redundancy across depth and enables the construction of wider and deeper networks within a fixed parameter budget. We further provide a
geometric interpretation of the neural bases from a vector-field perspective and extend the framework to linear projection modules. Experiments demonstrate that the LRNB architecture achieves comparable or lower final training loss than independently parameterized baselines while using fewer parameters and maintaining stable training dynamics. These findings support
neuron-level reuse as a practical approach to parameter-efficient network design.
Read the full abstract ▾
Machine Learning
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Tomáš Holeček and Viliam Lisý
Model-based reinforcement learning (MBRL) has achieved remarkable results in single-
agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-
agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-
Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient
algorithms and inherits their convergence guarantees towards Nash
equilibria under an idealized model. Empirical evaluations across five
benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of
algorithms to posterior collapse in
stochastic environments. We leave it as an open challenge.
Read the full abstract ▾
Computation and Language
SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue
Stephanie Fong, Yiwen Jiang, Zimu Wang et al. (+12 more)
Large
Language Models (LLMs) are increasingly used in advice seeking and decision making that may affect social judgements. Despite stigma's profound effects on people and communities,
benchmarks remain scarce. Existing general-domain evaluations typically rely on static
prompts and fixed-format tasks, overlooking conversational contexts and audience effects in everyday communication. To address these gaps, we introduce SDARE-Bench, the first scenario-based
benchmark evaluating both stigma detection and open-ended response generation in LLMs, comprising 1,138 dyadic queries and 1,388 group dialogue. Empirical results across 8 LLMs consistently demonstrate poor identification of stigma components, especially in group dialogues. In open-ended response generation, stigma expression was substantially higher in group settings than in dyadic, with weaker resistance to stigma and more unrealistic advice. Responses were evaluated using a classifier trained on 1,392 human annotated responses. In constructed group pressure settings, stigma expression rates further increased to a striking average of 97.5%. Our findings identify stigma response as a recurring LLM safety vulnerability, especially in socially complex conversational contexts.
Read the full abstract ▾
All authors Stephanie Fong, Yiwen Jiang, Zimu Wang, Hongxi Yang, Yaling Shen, Hiu Weh Naomi Chow, Heung Ying Lai, Xiangyu Zhao, Qingyang Xu, Zhongxing Xu, Jiahe Liu, Guilherme C. Oliveira, Vincent Lee, Zongyuan Ge, Dominic Dwyer
Machine Learning · Cross-listed from stat.ML
Variable Selection for Feature-Based Newsvendor
Zhaoliang Yuan and Jie Wang
Feature-based newsvendor models use observable
covariates to tailor inventory decisions, aiming to balance holding and shortage costs under demand uncertainty. However, high-dimensional feature sets often hinder interpretability and inflate data collection and implementation costs. This paper studies variable selection for the feature-based newsvendor problem under a hard cardinality constraint on the number of selected features. We formulate the resulting $\ell_0$-constrained empirical newsvendor problem with $\ell_2$-regularization, establish its computational hardness, and develop a mixed-integer second-order cone programming reformulation that strengthens the standard Big-$M$ formulation. To enable scalability beyond exact optimization, we develop a randomized-rounding
algorithm with a bi-criteria guarantee and a greedy heuristic. Statistically, we provide theoretical analysis of the resulting sparse policy
estimator, including finite-sample estimation error, out-of-sample risk bounds, and support recovery guarantees. Extensive experiments on both synthetic and real data illustrate the computational and statistical trade-offs among various baselines. Our results demonstrate that the proposed variable selection framework achieves competitive out-of-sample operational costs while using substantially fewer
covariates.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Generalized Semi-Infinite Programming for Robust Optimal Control with Decision-Dependent Uncertainty
J. Wehbeh, E. C. Kerrigan and E. Scaccia
Generalized semi-infinite programs (GSIPs) arise in robust optimal control whenever the admissible uncertainty depends on the state or controls. Existing GSIP methods either impose restrictive structural assumptions or require global optimization that scales poorly to control problems. We present a general framework that reformulates any GSIP with mild regularity as an existence-constrained semi-infinite program, smoothing its disjunctive feasibility condition into differentiable existence constraints over a fixed index superset. The resulting program is solved by established adaptive discretization (cutting-plane) methods using only off-the-shelf nonlinear-programming solvers, and converges under standard assumptions. Treating the state trajectory as part of the uncertainty extends the framework to robust nonlinear optimal control with state-dependent uncertainty. We demonstrate it on a nonconvex
benchmark GSIP and a satellite de-tumbling problem with dynamically varying inertia.
Read the full abstract ▾
Machine Learning
Quantum Sparse Autoencoders for Q-Matrix Estimation in Cognitive Diagnosis
Arif Hassan Zidan, Yi Pan, Bowen Guo et al. (+5 more)
Q-
matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires. Data-driven Q-
matrix estimation remains challenging when assessments involve many correlated skills and when real response patterns depart from idealized generative assumptions. We introduce a novel
quantum sparse autoencoder (QSAE) for Q-
matrix estimation, which, to the best of our knowledge, is the first application of
quantum machine learning (QML) to cognitive diagnosis. Overall, the QSAE embeds each student's binary response vector into a
quantum circuit using an encoder, compresses it into a sparse latent representation, and maps that representation to the Q-
matrix. We
benchmark the QSAE against a classical autoencoder (CAE) across 60 simulated
datasets and 9 real-world assessment
datasets. The results reveal complementary strengths. Although the CAE partially achieves higher average accuracy under several simulation conditions, the QSAE is substantially more stable across replications, exhibiting lower variance in 49 of the 60 conditions. Moreover, on real assessment data, the QSAE outperforms the CAE on 6 of the 9
datasets. These findings suggest that the principal advancement of QML in this setting is not universal accuracy improvement, but enhanced robustness and capability to explore latent-structure complexity in real
datasets.
Read the full abstract ▾
All authors Arif Hassan Zidan, Yi Pan, Bowen Guo, Xiang Li, Yu Bao, Yingfeng Wang, Tianming Liu, Wei Zhang
Multimedia
Can LLMs Design Video Coding Tools? A Case Study on Planar Mode
Yingwen Zhang, Meng Wang, Liqiang He et al. (+1 more)
This paper explores whether large
language models (LLMs) can design
video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in
video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predictors, encoder trials evaluating their coding performance, and the LLM re-generating refined implementations based on the evaluation feedback. We first examine directly replacing the default Planar mode in the Fraunhofer Versatile
Video Encoder (VVenC) under its faster preset. Experimental results demonstrate that the LLM-generated mode can outperform the conventional Planar mode on this lightweight toolset, achieving 0.18% bitrate savings with 0.4% complexity overhead on the standard
benchmark. We further extend our evaluation to the Enhanced Compression Model (ECM). Leveraging newly introduced directional Planar modes, we investigate two integration strategies: directly replacing them, and introducing the LLM-generated predictor as an additional prediction mode with new syntax elements. The empirical results suggest that both strategies can yield coding gains under a constrained low-resolution setting. Overall, this study offers preliminary evidence and practical insights, highlighting both the potential and open challenges of LLM-based coding tool design.
Read the full abstract ▾
All authors Yingwen Zhang, Meng Wang, Liqiang He, Shiqi Wang
Computation and Language
Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
Jacqueline He, Howard Yen, Shuyue Stella Li et al. (+9 more)
Logit-based knowledge
distillation (KD) is used to train smaller
language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across training stages remains unclear. Through controlled experiments, we find that forward Kullback-Leibler (KL)
distillation–the standard KD formulation–with post-trained teachers behaves fundamentally differently during mid-training, an intermediate phase of self-supervised learning on curated corpora. Surprisingly, while forward KD simultaneously improves
reasoning and factual recall during pre-training relative to standard next-
token prediction (NTP), it instead slows factual recall acquisition during mid-training despite continued
reasoning gains. We trace this stage dependence to an asymmetry in teacher confidence across data domains and the student's evolving knowledge state: teachers are more confident on procedural than knowledge-intensive data, while students acquire low-
entropy factual knowledge earlier in training. To mitigate this imbalance, we propose Switch
Distillation, a simple mid-training objective that distills on
tokens where the teacher is confident, using teacher predictive
entropy as a lightweight routing signal, and otherwise falls back to cross-
entropy. Switch
Distillation consistently outperforms existing
distillation objectives across teacher sizes. Relative to standard NTP, it achieves 1.61-1.71x the
reasoning performance and 1.13-1.19x the knowledge and commonsense performance while preserving 96.7-96.8% of factual recall. Crucially, these benefits persist after post-training: Switch
Distillation closes the factual recall gap while maintaining 1.25-1.32x and 1.13-1.20x gains in
reasoning and knowledge and commonsense, respectively.
Read the full abstract ▾
All authors Jacqueline He, Howard Yen, Shuyue Stella Li, Margaret Li, Hanqing Zeng, Yinglong Xia, Benyu Zhang, Zhuokai Zhao, Qiang Zhang, Pang Wei Koh, Luke Zettlemoyer, Wen-tau Yih
Computer Vision
Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison
Thibaut Loiseau, Guillaume Bourmaud and Vincent Lepetit
Self-supervised pre-training via cross-view completion learns strong features for 3D
vision from co-visible regions of image pairs. However, the reference view provides little information for reconstructing non-co-visible patches, implicitly yielding a
monocular training signal in these regions. We introduce Gekko, which turns this limitation into a useful signal. The relative improvement of the cross-view reconstruction error over a masked-autoencoder error is a self-supervised proxy for co-visibility: large improvements indicate co-visible regions, negligible ones non-co-visible areas. Gekko is a network, trained from scratch, that jointly performs cross-view completion, masked autoencoding, and per-pixel prediction of this relative improvement, providing an additional binocular signal for all masked regions without any ground-truth 3D annotation. Under identical architectures and training data, Gekko consistently outperforms CroCo on zero-shot correspondence estimation, relative pose estimation, and pointmap regression, with up to 6 times higher accuracy at the strictest relative-pose threshold and a 22% drop in end-point error on ETH3D. The extra channel it learns is itself a strong co-visibility detector on unseen scenes, and Gekko's frozen features outperform released cross-view backbones of comparable or larger size. It can also be trained directly from raw
videos with a simple stride-based curriculum, removing the cumbersome 3D preprocessing prior methods require while matching models trained on curated data. Code and pre-trained models are publicly available.
Read the full abstract ▾
Information Theory · Cross-listed from math.PR
Multiplicative comparisons of Rényi entropies for weighted Bernoulli sums
Jiange Li
We establish multiplicative comparisons between Rényi
entropies of different orders for weighted sums of independent Bernoulli random variables. In particular, we prove a logarithmic comparison between the zeroth- and infinity-order Rényi
entropies, which yields a
polynomial improvement over the square-root bound of Jain, Sah, and Sawhney. As an application, this leads to an improved parameterized running time for the randomized bin-packing
algorithm of Nederlof, Pawlewicz, Swennenhuis, and Wȩgrzycki. We also obtain explicit dimension-free, constant-factor comparisons between Rényi
entropies of positive orders.
Read the full abstract ▾
Computational Geometry
Sierpiński–Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation
Sebastien Tchitchek and Julien Tierny
This paper introduces the Sierpiński-Knopp (SK) Wasserstein distance, a fast metric between persistence diagrams. The SK-Wasserstein distance, denoted $d_{\mathrm{SK}}$, maps diagram points and their diagonal projections to the unit interval via the Sierpiński-Knopp space-filling curve on the upper diagonal triangle. The encoded point sets are then efficiently matched via one-dimensional optimal assignment, in \(O(N\log N)\) steps, yielding an explicit diagonal-aware point assignment between the two input persistence diagrams. We show that the SK-Wasserstein distance controls the classical \(2\)-Wasserstein distance between diagrams, admits an explicit isometric
embedding into a
Hilbert space, and induces a positive-definite Gaussian kernel, making the resulting geometry directly compatible with Euclidean and kernel-based learning methods. A tighter surrogate dissimilarity, noted \(W_\Gamma\), is also introduced based on the point assignments along the curve. Experiments on 12 scientific collections comprising 227 diagrams show median per-collection speedup of \(d_{\mathrm{SK}}\) over state-of-the-art approximations of \(W_2\) is \(626\times\), while the aggregate speedup over the full
benchmark is \(2100\times\). Average-linkage partitions obtained from \(d_{\mathrm{SK}}\) and \(W_\Gamma\) each exactly match the corresponding \(W_2\) partition on 8 of the 12 collections.
Hilbert \(k\)-means and Gaussian spectral clustering, both based on \(d_{\mathrm{SK}}\), achieve mean adjusted Rand indices (ARI) of \(0.756\) and \(0.800\), respectively, with respect to the
benchmark reference partitions, compared to \(0.750\) obtained by average linkage on \(W_2\). The Gaussian \(d_{\mathrm{SK}}\) kernel supports other kernel-based analysis tasks, as illustrated by its use for contiguous
segmentation of ordered diagram collections in our experiments.
Read the full abstract ▾
Hardware Architecture
Performance Characterization of SPEC CPU 2026 on AMD EPYC 9755 Processor
Kunal Kashyap, Rajiv Ramanathan and Shayantika Bhattacharya
SPEC CPU 2026 is the first major update to the industry-standard CPU
benchmark suite since 2017. This paper presents the first microarchitecture based performance characterization of the new suite, conducted on AMD EPYC "Zen 5", also the first SPEC CPU characterization study on this microarchitecture. Using a multi-lens methodology spanning pipeline efficiency, control flow behavior, cache hierarchy pressure, and instruction mix, we analyze both SPECrate and SPECspeed suites. We introduce scale analysis, comparing single-copy to full-system behavior to expose system-level bottlenecks invisible to conventional characterization. Our analysis reveals substantial behavioral diversity across the suite, and the multi-lens analysis identifies three distinct behavioral clusters: frontend control-flow-dominated workloads that stress branch predictor throughput rather than accuracy, high-efficiency compute workloads that suffer SMT contention at scale, and
memory bandwidth-bound workloads with poor L3 filtering even at single-copy. Scale-dependent effects, including SMT dispatch contention causing throughput reduction and L3 capacity interference, emerge only at full system utilization. This work establishes an empirical foundation for architectural research and workload-driven design decisions targeting next-generation datacenter processors.
Read the full abstract ▾
Artificial Intelligence
EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
Qing Zhao, Haowei Li, Weijian Deng et al. (+3 more)
Scientific discovery depends on the ability to form hypotheses, test them through experiments, and revise them when evidence disagrees. Existing LLM
agents support this process by improving their
reasoning or actions, but their scientific beliefs are often scattered across free-form
reasoning and difficult to update coherently. This makes it difficult to identify what failed, what should change, and whether revisions remain consistent with prior evidence. We introduce EvoSCM, which represents scientific beliefs as a population of structural causal model (SCM) hypotheses that can be tested and revised across experiments. EvoSCM formulates scientific discovery as a closed loop in which causal hypotheses guide experimentation and experimental outcomes drive causal model
evolution. Competing SCM hypotheses make falsifiable predictions and guide discriminative experiments that separate alternative explanations. When observations contradict these predictions, EvoSCM distills discrepancies into correction rules identifying which aspects of the hypotheses fail to explain the evidence. These rules guide revisions to causal dependencies, latent factors, mechanisms, and parameters. Revised hypotheses are validated against accumulated evidence and carried forward to guide subsequent experiments, allowing scientific beliefs to evolve cumulatively. We evaluate EvoSCM across physics, chemistry and materials, and biology. It consistently outperforms baseline
agents and existing
evolution methods, yielding more accurate explanations and predictions with more effective use of experimental budgets. The evolved SCMs also transfer across base models, suggesting reusable scientific knowledge beyond any single model's
reasoning process.
Read the full abstract ▾
All authors Qing Zhao, Haowei Li, Weijian Deng, Sibei Yang, Pengxu Wei, Liang Lin