Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Thursday 27 August

Robotics

FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

Zekai Li, Jiaming Tang and Zhijian Liu

Vision-Language-Action (VLA) models are increasingly promising for robotic manipulation, yet their real-world deployment remains bottlenecked by high inference latency and unstable asynchronous execution. This challenge is particularly pronounced in flow-matching-based VLA models, where action decoding requires multiple iterative steps conditioned on the VLM context. While efficient inference methods improve control frequency and asynchronous methods reduce execution idle time, existing approaches often fail to jointly achieve low-latency inference and accurate, temporally consistent asynchronous execution. We introduce FlashVLA, a streaming action decoding framework that addresses both challenges in a unified formulation. FlashVLA maintains a streaming action buffer with multiple chunks at different noise levels and decodes them using chunk-wise causal attention. This design allows FlashVLA to produce one executable action chunk per inference step. Moreover, its chunk-wise autoregressive formulation implicitly preserves action continuity, enabling smooth asynchronous execution without extra future-state conditioning. Across extensive simulated and real-world experiments, FlashVLA substantially improves inference speed while maintaining strong task performance. It can achieve $\geq$30\,Hz control frequency on a single GPU with smooth asynchronous inference in real-world deployment.
Read the full abstract

Game Theory

Token-Level Advertising

Hanbing Liu, Bowei Zhang, Changyuan Yu et al. (+2 more)

Generative AI is transforming how people access information, challenging traditional advertising mechanisms built around predefined slots. Towards generation-native advertising, we propose the Latent Advertiser Mixture Auction (LAMA), a token-level advertising mechanism that embeds advertiser influence directly into the generation process. Advertisers report local continuation values that induce advertiser-specific next-token policies, from which the platform decodes through a latent mixture while updating an allocation posterior. We show that LAMA satisfies Markov DSIC and IR, and achieves near-optimal KL-regularized welfare. We further develop a learning-based implementation that reconstructs the required reports online from learned local advantages and root values. Proof-of-concept experiments on real-world commercial-search query splits show that LAMA improves platform welfare and revenue while maintaining user-facing response quality, providing initial evidence for the feasibility of generation-native advertising.
Read the full abstract

All authors Hanbing Liu, Bowei Zhang, Changyuan Yu, Yinyu Ye, Qi Qi

Discrete Mathematics · Cross-listed from math.CO

Boxicity and Threshold Dimension of Zero Divisor Graphs

Marco Caoduro and Meike Neuwohner

The zero divisor graph $\Gamma(R)$ of a finite commutative ring $R$ has as vertices the non-zero zero divisors of $R$, with an edge between two elements exactly when their product is zero. We determine the boxicity and threshold dimension of $\Gamma(R)$ for two classes of finite commutative rings: reduced rings and quotients of principal ideal domains. Our proofs use a new combinatorial gadget, the integral covering graph, that captures the structure shared by both ring families and generalizes the disjointness graph on subsets of $[n]$, where two subsets are adjacent if and only if they are disjoint. In doing so, we answer two questions recently posed by L.~Sunil Chandran and Suraj Kumar Sahoo in Boxicity of Zero Divisor Graphs, Discrete Applied Mathematics 391 (2026).
Read the full abstract

Computation and Language

D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection

Xin Chen, Fuwei Zhang, Yiqi Tong et al. (+3 more)

AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated. This framing breaks down for mixed-origin writing, where content origin and expression origin may differ. We cast mixed-origin detection as dimension-to-composition source attribution, inferring content origin and expression origin before composing them into four collaboration types. We propose Dimension-to-Composition Routing (D2C-Routing), which routes content-side and expression-side evidence to supervised dimension heads before a learned gated composition layer predicts the final label. On MixD2C, a reconstructed split derived from the HART mixed-origin benchmark, our disclosed D2C-Routing-based detector system reaches 0.8603 four-way Avg TPR@1%FPR, 6.5 points above the same-split RACE-local rerun. Core ablations support the routing design, while error analysis shows that distinguishing AI-content/human-expression from fully AI-generated text remains the hardest boundary. Code is available at https://github.com/bystander563/d2c-routing-artifact.
Read the full abstract

All authors Xin Chen, Fuwei Zhang, Yiqi Tong, Wei Guo, Yutian Xiao, Fuzhen Zhuang

Data Structures and Algorithms · Cross-listed from math.PR

Universality and sharp thresholds for ellipsoid fitting

Frederic Koehler and Youngtak Sohn

We establish a sharp phase transition for fitting random vectors by an ellipsoid. The random vectors have independent subgaussian coordinates with mean zero, variance one, and a common fourth moment, and the number of vectors is proportional to the square of the dimension. We identify an explicit satisfiability threshold such that, with high probability, a positive definite ellipsoid passes through every data point below the threshold, whereas no positive semidefinite fit exists above it. We also determine the optimal squared fitting error throughout the unsatisfiable regime. In particular, the threshold depends on the coordinate distributions only through their common fourth moment, revealing a fourth moment universality phenomenon. For standard Gaussian data the threshold is $1/4$, resolving the ellipsoid fitting conjecture.
Read the full abstract

Robotics

Embodied Scene Rearrangement Planning

Canzhi Chen, Zan Wang, Siqi Zhu et al. (+3 more)

This paper introduces Embodied Scene Rearrangement Planning (ESRP), a novel task requiring embodied agents to rearrange furniture in 3D scenes to match a target configuration using only egocentric observations and a top-down target layout. Unlike prior rearrangement tasks, ESRP precludes global state access and introduces mutual object occlusions, reflecting the practical constraints of real-world robotic deployment. These factors make aligning partial egocentric observations with the global target layout particularly challenging for long-horizon planning. To facilitate research, we present ESRP-Bench, a comprehensive benchmark built on OmniGibson featuring over 5,400 scene pairs and 8,200 objects. We define three multi-level metrics to evaluate rearrangement quality and provide four baselines: a hierarchical task-and-motion planning method, a vision-language-model-based method, and two learning-based approaches (IL and RL). Experimental results demonstrate that current methods struggle to complete the task efficiently, highlighting ESRP as a challenging frontier for embodied agents in scene understanding and long-horizon task planning. This work serves as a stepping stone toward deploying intelligent agents in real-world scenarios. Project page: https://pie-lab.cn/ESRP/.
Read the full abstract

All authors Canzhi Chen, Zan Wang, Siqi Zhu, Qi Wu, Yixuan Li, Wei Liang

Computation and Language

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Kairong Luo, Jiarui Cui, Yaorui Yin et al. (+8 more)

Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communities. Although strong open-source efforts already exist, including open-weight models and open-source training recipes, a cost-efficient, hardware-accessible, and open-source pretraining recipe has long been missing. Even at a small scale, training Llama-3.2-3B costs over \$1.5M, and reproducing SmolLM3-3B needs over \$700K. In this report, we present an open pretraining recipe designed to lower this barrier. Using this recipe, we train a collection of Puro-2B models from scratch on up to 1.4 trillion tokens with FP8 precision on consumer-grade RTX 5090 GPUs. The models in the collection differ in token budgets and selected recipe variants. Our best model is trained at a compute cost of less than \$6.9K and approaches Qwen2.5-1.5B performance under our evaluation protocol. This cost efficiency is enabled by a combination of approaches, including hardware selection, low-precision training, hyperball optimization, curriculum model averaging, and the data recipe. Beyond the recipe itself, we provide two additional results. First, across the Puro-2B collection, we derive a Puro Cost Scaling Law that relates training cost to average model performance; the fitted law suggests that about \$4.4K, less than \$5,090, is sufficient to reach the performance of Qwen2-1.5B. Second, as an end-to-end case study, we examine how pretraining data curricula shape downstream performance after post-training. Such controlled studies are enabled by having access to the full pretraining pipeline rather than model weights alone. We release the full training recipe for Puro-2B, including data, code, and model weights under Apache 2.0 at https://huggingface.co/collections/thu-pacman/puro-2b.
Read the full abstract

All authors Kairong Luo, Jiarui Cui, Yaorui Yin, Shengqi Chen, Yiming Yang, Linxiang Gao, Yanmohan Wang, Chengxia Li, Mingzhe Zhang, Kaifeng Lyu, Wenguang Chen

Computer Vision

Successive Capacity Growth: Task-Complexity-Driven Width and Depth Expansion for Vision Transformer Encoders in JEPA World Models

Frederik Berenz

Joint-Embedding Predictive Architectures (JEPAs) for world modeling typically employ fixed-size Vision Transformer encoders that are over-provisioned for simple tasks and under-provisioned for complex ones, with significant redundancy across attention heads. We propose Successive Capacity Growth (SCG), a method that starts from a minimal encoder (1 head, 2 layers, 283K parameters) and grows incrementally in width (adding attention heads for low-level semantic capacity) or depth (adding transformer blocks for higher-order semantic abstraction), driven by a task-agnostic test-and-verify mechanism that exploits function-preserving expansion to safely trial architectural changes and roll back if they do not improve prediction loss. The Sketched Isotropic Gaussian Regularizer (SIGReg) ensures that all learned semantic dimensions remain statistically independent and aligned with the predictive objective, preventing collapse even as the architecture grows. On a 60-dimensional multi-object dynamics task, SCG naturally triggers depth expansion, improving prediction loss by 20.3% over the fixed small baseline with 56 times greater parameter efficiency than scaling to the fixed large model; on a 2D navigation task, a single width expansion yields even an 23% improvement over the fixed large model. Across all three tested environments of increasing complexity, the adaptive encoder matches or exceeds the fixed small baseline, with zero false-positive expansions and bit-exact function preservation (ratio = 1.0, absolute difference = 0.0). The take-away is that JEPA world model encoders need not be pre-allocated at maximum capacity - they can grow successively as the task demands, achieving significant compute and data efficiency while maintaining representation quality.
Read the full abstract

Information Retrieval

Stageboost: Recommending Signals Based on Counterfactual Estimation

Darpan Singhal, Matan Mandelbrod, Tal Franji et al. (+3 more)

Signals are short textual or visual snippets displayed on the eBay View-Item (VI) page, providing additional, contextual information for users about the viewed item. The aim of displaying these signals is to facilitate intelligent purchase and to incentivize engagement. In this paper, we present a 2 stage xgboost based model that optimally populates the VI page with signals. This approach has shown a 0.08% lift in overall GMB (Gross Merchandise Bought) and 0.58% increase in Parts and Accessories GMB, primarily due to increase in conversion of high average price items in online experimentation.
Read the full abstract

All authors Darpan Singhal, Matan Mandelbrod, Tal Franji, Manasa Kolla, Vipul Gaba, Yuri Brovman

Computer Vision

KnockGS:interaction-Grounded Calibrationof Physical Gaussian Representations

Chenchen Ge, Hanwen Shen, Bowen Jing et al. (+6 more)

Physics-integrated 3D Gaussian representations now allow reconstructed deformable objects to be simulated and rendered under explicit material models. Existing pipelines, however, assume that material parameters are known or manually specified, limiting their applicability when these parameters must be inferred from observed object dynamics. We propose KnockGS, an interaction-response PhysicalGS framework that estimates the elasticity and density scales of a 3D Gaussian object from its dynamics under a known applied force. Rather than treating physical simulation only as a forward process, we turn the force-induced response into a calibration signal: temporal response features are xtracted from the observed dynamics, the two material scales are estimated from those features, and the estimate is then frozen and written back into the same simulator so that it can be tested on an interaction it was never fitted to.We evaluate the framework on both parameter recovery and response-level fidelity. The estimated scales are compared against hidden ground truth, and the re-simulated object is measured against the target using 3D particle trajectories, response-curve statistics, and rendered-frame quality. Across five held-out material targets, our method recovers the scales substantially more accurately than response retrieval, global regression, or a fixed default material, and the frozen estimate remains predictive under interactions that differ in direction and in magnitude. Interaction response therefore carries enough information to calibrate material scales in physically grounded 3D Gaussian representations.Our study is a first step toward interactive PhysicalGS systems that calibrate a Gaussian asset whose rendered appearance and simulated response are consistent.
Read the full abstract

All authors Chenchen Ge, Hanwen Shen, Bowen Jing, Jiyuan Cai, Xiaofeng Wang, Hongsen Lei, Weitao Zhou, Dandan Zhang, Haibao Yu

Artificial Intelligence

Sophistication in GenAI Use: Field Evidence from a Large Firm

Nicholas J. Hallman, Zachary T. Kowaleski, Anu Puvvada et al. (+1 more)

We study how sophistication in generative AI (genAI) use varies among the back-office workforce of a large firm. Using proprietary data, we observe 713,564 employee prompts and their corresponding large language model responses from nearly 4,000 back-office employees across 15 functional areas over eight months in 2025. We document three main findings. First, senior employees exhibit more sophisticated genAI use, consistent with domain expertise complementing genAI capabilities. Second, sophistication varies considerably across functions and is highest in Strategy, Digital Innovation, and Project Management, three groups that share a focus on firmwide strategic initiatives and organizational change. Third, we observe neither improvements in sophistication over time nor lasting improvements following formal AI training, suggesting that sophisticated use can be difficult to change. Together, our study provides measures of and insights into sophisticated genAI use that managers can use to improve outcomes and that researchers can use in future research.
Read the full abstract

All authors Nicholas J. Hallman, Zachary T. Kowaleski, Anu Puvvada, Jaime J. Schmidt

Computation and Language

Your Voice Cloning System is Secretly a Voice Anonymizer

Romolo Muletta, Felix Matthias Saaro, Mark Cieliebak et al. (+1 more)

Speaker anonymization suppresses speaker-identifying attributes from speech while preserving linguistic content and quality. We propose repurposing XTTSv2, a multilingual voice cloning model trained on 27k hours of speech, for speaker anonymization without retraining. Our key insight is that XTTSv2's voice cloning capabilities preserve prosodic structure independently of speaker identity, enabling voice conversion by conditioning on a pseudo-speaker. We introduce an iterative refinement strategy that balances privacy and utility by maximizing a harmonic mean of speaker dissimilarity and intelligibility. Evaluated on seven European languages across CommonVoice and Multilingual LibriSpeech, our system achieves near-optimal privacy (EER $\approx$ 0.49), competitive intelligibility, and substantially better speech quality than dedicated anonymization baselines, while requiring no language-specific training. We release the code here: https://github.com/rm00cr/coqui-tts.
Read the full abstract

All authors Romolo Muletta, Felix Matthias Saaro, Mark Cieliebak, Jan Deriu

Computation and Language

RCMN: Understanding Misleadingness in Influential Public Discourse

Peiling Yi

Influential public discourse shapes public beliefs and can also mislead, not only through what is stated, but also through how information is framed, omitted, contextualised, and communicated. Yet less research has focused on how such misleadingness arises and shapes the interpretations formed by readers. To address this gap, we introduce Reader-Centric Misleadingness Understanding (RCMN), a framework that operationalises misleadingness through five dimensions: misleading mechanism, likely reader interpretation, evidence-warranted interpretation, emotional arousal, and communicative intent. Based on this framework, we construct an evidence-grounded dataset of influential public discourse. Empirical findings show that misleadingness is diverse and extends well beyond fabrication, with unsupported inference, exaggeration, and omission among the prevalent mechanisms, and is frequently associated with heightened emotional arousal and distortive communicative intent. Moreover, we investigate whether lightweight claim-and-context representations retain sufficient cues for understanding reader-centric misleadingness without access to richer contextual, evidential, and multimodal information. Evaluation across five recent generative foundation models shows that reader-level interpretations can often be recovered from such limited representations, whereas identifying how misleadingness is produced remains considerably more challenging. These findings highlight the potential of lightweight representations for scalable misleadingness analysis, while reliable understanding of misleading mechanisms continues to require richer contextual and evidential grounding.
Read the full abstract

Machine Learning

Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO

Yunpeng Ba, Zhi Zheng, Yue Xie et al. (+7 more)

Evolution Strategies (ES) have recently emerged as a memory-efficient post-training paradigm for LLM reasoning. However, the optimization behavior of ES remains understudied, making it hard to define its advantage scope compared to mainstream post-training paradigms (e.g., Group Relative Policy Optimization (GRPO)). By systematically investigating ES dynamics and mechanisms, this paper first identifies a performance advantage of ES over GRPO, theoretically and empirically showing that ES can lead to broader reasoning coverage, thereby better exploiting the reasoning capabilities of pretrained LLMs. Theoretically, we show that verifier-projected Jensen-Shannon diversity across the ES population is helpful to higher Pass@K performances. Empirically, unlike GRPO, which exhibits entropy collapse, ES improves Pass@1 while attaining higher Pass@K than GRPO. We further develop a sequential GRPO-ES training strategy that combines GRPO's strength in Pass@1 with ES's gains in Pass@K. Second, we find that despite substantial whole-model parameter drift, the task-performance gains of ES are only contributed to a sparse subset of larger-magnitude updates. This functional sparsity suggests that large parameter movement need not imply widespread functional change, and held-out evaluations further show that it does not necessarily lead to catastrophic forgetting. Finally, we study how hyperparameter design affects the effectiveness of ES, demonstrating that ES requires a smaller population size in a larger LLM. These findings position ES as a distinct reasoning post-training paradigm rather than a less effective, memory-efficient alternative to GRPO.
Read the full abstract

All authors Yunpeng Ba, Zhi Zheng, Yue Xie, Jiaqing Li, Xialiang Tong, Tao Zhong, Mingxuan Yuan, Zhichao Lu, Xuyang Wu, Zhenkun Wang

Computation and Language

INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment

Yutong Zhang, Jianshuo Dong, Peng Xu et al. (+5 more)

As large language models (LLMs) are deployed as autonomous agents, safety failures increasingly involve consequential actions. We study agentic misalignment, where agents take harmful actions under goal conflicts and pressures. Using chain-of-thought (CoT) monitoring, we find that harmful execution is often preceded by intent signals in reasoning. However, post-hoc CoT labels are too coarse to show how intent changes during generation. We introduce INTENT-AS-A-TOOL, an approach that adds intent-targeted tools to give the model a dedicated channel for expressing commitment to a target behavior. The probability of calling an intent tool provides a judge-free, fine-grained signal of the model's tendency to pursue that behavior. Our results show that INTENT-AS-A-TOOL complements CoT monitoring, expands post-hoc CoT labels into dense trajectories, and identifies critical steps for online intervention. These findings suggest that action preferences are useful for tracking agentic misalignment during reasoning. Our code and data are accessible: https://github.com/RebeccaZhang22/intent-as-a-tool.
Read the full abstract

All authors Yutong Zhang, Jianshuo Dong, Peng Xu, Long Wang, Jie Zhang, Tianwei Zhang, Xiaoping Zhang, Han Qiu

Game Theory

Blindfolded pursuit with delays of your choice

Torben Schürenberg and Maximilian J. Stahlberg

We study pursuit-evasion games on graphs with a single pursuer and an invisible evader. The pursuer may assign integer travel times to the edges of the graph and specify a finite sequence of vertices to query, one per time step. The evader then chooses a walk over the same time horizon, aiming to elude all queries. With unit travel times, the setting in which the evader must move at every time step is known as the hunter and rabbit game, while the variant in which the evader can wait at a vertex can be phrased as a firefighting game: the vertices of a burning graph must be extinguished, and any vertex left burning reignites its neighbors. For both settings, we show that the power to choose travel times allows a single pursuer to succeed in polynomial time on any graph. This contrasts with unweighted graphs, where the number of hunters or firefighters needed can grow linearly in the number of vertices. If the evader, in addition to waiting, may start at an earlier time unknown to the pursuer, we show that the pursuer still wins on any graph given exponential time.
Read the full abstract

Computer Vision

PAWBench: How Far Are We from Probabilistically Aligned World Modeling?

Yuandong Pu, Le Zhuo, Sayak Paul et al. (+11 more)

Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not only a plausible trajectory, but also the distribution of possible behaviors under the same initial observation and action. We call this distribution-level requirement probabilistic alignment. However, existing evaluations largely assess individual-video plausibility and do not test whether repeated generations recover the correct distribution. This raises a central question: how far are current video generators from probabilistically aligned world modeling? To answer it, we formalize probabilistic alignment as a distributional criterion for world models and introduce PAWBench, a benchmark for evaluating video generators as stochastic samplers of world dynamics. We further introduce PAWEval, an outcome-level protocol that converts repeated video rollouts into empirical distributions over possible physical behaviors. Across 50 scenarios and eleven current systems, no model consistently matches the reference probabilities while recovering the range of valid behaviors. Having established this gap, we test whether language prompts, initial noise sampling, or model training can reshape the model's predictive distribution. We believe our work can serve as a foundation for future efforts to move towards probabilistically aligned world modeling.
Read the full abstract

All authors Yuandong Pu, Le Zhuo, Sayak Paul, Gabriel Jorge Menezes, Avram {\DJ}or{\dj}ević, Shiyang Li, Yifan Zhou, Bin Fu, Wenlong Zhang, Junjun He, Yu Qiao, Yihao Liu, Jinbo Xing, Xi Chen

Computation and Language

Pair-Level Essay-Scale Republication and Reuse from Fragmented Historical Text Reuse: A Workflow Study on Eighteenth-Century Books and Newspapers

Ke Shu, Kira Hinderks, Eetu Mäkelä et al. (+1 more)

This paper addresses the recovery of essay-scale republication and reuse from fragmented text-reuse evidence, a setting whose central challenge is pair-level evidence consolidation and not fragment retrieval alone. The study focuses on a candidate set centered on essays by eighteenth-century Scottish philosopher David Hume, spanning books from ECCO (Eighteenth Century Collections Online) and historical newspapers. Because the input consists of fragmented reuse hits instead of clean document pairs, and positive coverage is inherently incomplete, we formulate the task as pair-level evidence consolidation into plausible transmission relations and compare three methodological families: a staged rule-based workflow, baselines (a decision tree and two direct LLM settings), and automated rule adaptation. On labeled ECCO–ECCO slices, pair-level feature aggregation alone already reaches 0.948 F1 on the main labeled slice, while the final workflow gives the strongest overall precision-recall trade-off among the tested rule stages. On the full ECCO–ECCO candidate universe, direct LLM baselines flag up to 14,886 pairs as reprints compared to 771 for the final workflow, behaving in this direct-prompt setup as high-recall candidate expanders rather than precision-controlled deployment classifiers. On ECCO–Newspaper, manual audit confirms all 176 predicted positives as genuine cases of republication or reuse, while issue duplication and source-side multiplicity reveal additional provenance structure. Under incomplete ground truth, auditable pair-level evidence consolidation provides a practical way to produce compact candidate spaces for historical inspection.
Read the full abstract

All authors Ke Shu, Kira Hinderks, Eetu Mäkelä, Mikko Tolonen

Artificial Intelligence

Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance

Allison Zhuang and Santiago Aranguri

Steering interventions targeting eval-awareness, a model's recognition that it is being tested, are increasingly used in safety evaluation pipelines, where evaluation-awareness is treated as a single quantity to be suppressed. We show that verbalized eval-awareness in chain-of-thought can be identified as capabilities-flavored ("the user is testing my ability to follow instructions"), safety-flavored ("the user is testing my boundaries"), both, or neither: framings that predict compliance very differently. On Qwen3-32B over the FORTRESS dataset, capabilities-framing predicts compliance with a +24 to +46 percentage-point gap over safety-framing across all tested steering conditions. A CoT-prefill intervention on eval-awareness-negative rollouts suggests the link is causal, with 10 of 11 prefills shifting compliance in the predicted direction. Then, eval-awareness is not behaviorally uniform: aggregate suppression rates can move while the safety-relevant component does not, and the same "X% suppression of eval-awareness" can correspond to qualitatively different behavioral outcomes.
Read the full abstract

Machine Learning

Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting

Xinwei Qiang, Xiang Fang, Chang Chen et al. (+3 more)

Block drafters propose several tokens in one forward pass, before earlier target tokens are realised. Their rejection mixes two losses: missing within-block path information and imperfect modelling of observable information. Accepted length cannot distinguish them. We separate the two with an information floor, the minimum expected rejection at a specified conditioning order; rejection above this floor is the model gap. Measurements across four domains and four open-weight targets, plus floor estimates on a frontier API target, yield three findings. First, the all-parallel floor reaches $0.286$ at the final slot on Qwen3-4B, limiting even the best proposal to $71\%$ per-slot acceptance. Second, one realised token removes $86$–$100\%$ of this floor, a locality also recovered by an independent mutual-information analysis. Third, current drafters remain far above their floors: the final-slot model gap accounts for $43$–$64\%$ of DFlash rejection and $85$–$92\%$ of DSpark's oracle-conditioned rejection. Guided by this separation of short-range conditioning from proposal quality, we replace a context-independent predecessor correction with a prefix-attention head that reads committed context conditional on the predecessor. With supporting backbone components, the resulting Qwen3-4B drafter improves mean serving accepted length by $3.93\%$ over the released DSpark checkpoint across nine tasks, without increasing the conditioning order. Code and data: https://github.com/tie-pilot-qxw/specfloor; drafter checkpoints: https://huggingface.co/TIE-Pilot/dspark-attnconv-block7-qwen3-4b.
Read the full abstract

All authors Xinwei Qiang, Xiang Fang, Chang Chen, Zaifeng Pan, Yue Guan, Yufei Ding

Multiagent Systems

One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles

Zhichen Zeng, Huiyuan Chen, Jingru Cheng et al. (+7 more)

Specializing Large Language Models (LLMs) toward distinct abilities underpins successes ranging from personalized assistants to multi-agent systems (MAS). Single-agent paradigms rely on pre-defined personas or steering vectors to induce specialization, yet they impose a single fixed specialization that fails to adapt to diverse queries. Conversely, MAS achieves dynamic multi-perspective problem solving by orchestrating agents with distinct text-based roles, but fusing these specializations requires multi-turn interactions that inflate context length and inference cost. To address these limitations, we propose Mixture of Roles (MoRe), which adaptively composes multiple specializations into a single steering vector for single-turn inference. Specifically, MoRe learns a diversified codeboox of steering vectors, each of which encodes a latent role. A query-aware router dynamically fuses the codebook into a steering vector that encompasses multiple roles. By steering the backbone LLM with the composed vector, MoRe enables multi-perspective specialization in a single-agent, single-turn inference process. The proposed MoRe can be efficiently trained via a three-stage SFT curriculum and GRPO post-training, while the backbone LLM remains frozen. Experiments across reasoning and personality benchmarks show that MoRe outperforms single-agent baselines by 2.2% on average, and achieves performance on par with MAS while reducing token cost by 20x.
Read the full abstract

All authors Zhichen Zeng, Huiyuan Chen, Jingru Cheng, Juan Zha, Ming Liu, Ying Chen, Xiyuan Yang, Chaosheng Dong, Haiyang Zhang, Hanghang Tong

Distributed Computing

Consensus with Stochastic Broadcast

Pierre Fraigniaud, Boaz Patt-Shamir and Sergio Rajsbaum

We study binary consensus in the stochastic broadcast model, which assumes $n\geq 2$ processes communicating synchronously by message broadcasts. At each round, every process broadcasts a message to all the other processes. Each broadcast succeeds independently with some probability $p\in[0,1]$. If a broadcast succeeds, all processes receive the message, and if it fails, no process receives the message. The sender does not know whether its broadcast was successful or not. In this model, consensus is not solvable; the objective is to design, for a given number of rounds $r$, consensus algorithms that terminate in $r$ rounds, minimizing the probability of error disagreement. This problem has been studied in depth for 2 processes [DISC 2025]. We extend the study to $n> 2$.
Read the full abstract

Computation and Language

BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks

Jeong-Yoon Kim and Tae-Yoon Lee

Operational facilities accumulate extensive local telemetry, but agent-ready interactive evaluations with source-verifiable answers are costly to construct from such archives. Site-specific measurement histories also motivate a local conversion workflow that can operate where raw operational data must remain under organizational control. We introduce BTS-AgentBench, a deterministic compiler that transforms read-only telemetry and equipment metadata into tool-backed, multi-turn agent tasks, phase-level targets, evidence and executable evaluation contracts. The BTS release includes 532 episodes across nine families; a second-corpus port produces 204 XAI4HEAT episodes. Frozen-input replay reproduces released artifacts byte-for-byte, and independent raw-source checks cover all 89 BTS and 41 XAI4HEAT test episodes. Replayable provenance links 1,170 trial identities to recorded execution and scorer conditions, while 1,125 completed traces retain model responses and tool results. An obligation-level comparison of 216 scored failures found that linked records exposed additional recorded failed obligations in 202 cases (93.5%), including tool arguments, stream identity, state carryover and missing interaction steps. The pipeline thereby supports source-grounded task generation, exact reconstruction and auditable diagnosis of agent executions. Code, released benchmarks, and reproduction instructions are available at https://anonymous.4open.science/r/telemetry-benchmark-reproduction-3D68
Read the full abstract

Computer Vision

R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models

Qiwen Gu, Bingjie Gao, Rui Chen et al. (+7 more)

High similarity between first-visit and return frames does not necessarily show that a video world model remembered the scene; the intervening rollout may simply have changed very little. This ambiguity makes absolute revisit scores sensitive to rendering stability, repetitive content, and failed motion. We introduce R2M-Bench (Relative Revisit Memory Benchmark), a benchmark of observable revisit-selective consistency. For every detected return, R2M-Bench compares the revisit pair with two controls from the same rollout: a gap-matched non-revisit pair that measures generic temporal stability and a short-range pair that estimates short-horizon consistency. These comparisons produce MemoryGain (MG), the revisit advantage over the temporal baseline, and the Normalized Memory Ratio (NMR), which normalizes this advantage by the short-to-baseline dynamic range. R2M-Bench combines 100 reference scenes with three leave-and-return trajectories to form 300 instances and evaluates appearance fidelity, scene and object identity, local geometry, and persistent state. Across seven action-conditioned video world models, Overall NMR correlates with human consistency judgments at Spearman's $\rho=0.547$ (95% CI $[0.45,0.63]$). Its within-model correlation magnitude with generated motion is $0.072$, compared with $0.207$ for raw revisit similarity, indicating that relative calibration substantially reduces the slow-motion shortcut. DreamX-World-Memo achieves the highest Overall NMR among the evaluated video models. Together, these results support same-rollout relative calibration as a practical way to distinguish revisit-specific consistency from generic temporal stability.
Read the full abstract

All authors Qiwen Gu, Bingjie Gao, Rui Chen, Geng Li, Jifan Li, Qishuai Wen, Li Niu, Jing Tang, Xiangxiang Chu, Junqiao Zhao

Systems and Control

Why Three Phases? A Historical and Engineering Reassessment of Phase Order in AC Power Transmission

Kai Sun

Three-phase alternating current is so deeply embedded in modern electric-power infrastructure that its phase order is often treated as self-evident. Historically, however, 1-phase and true 2-phase systems were commercially important, while commercial 6-phase transmission was later demonstrated. This paper reassesses why 3 phases became the dominant architecture for bulk AC transmission. A general balanced \(m\)-phase formulation is used to show that constant aggregate instantaneous power is not unique to 3 phases: an ideal balanced 2-phase system also cancels the double-frequency power term and can generate a constant-magnitude rotating field. Consequently, the historical displacement of 2 phases cannot be explained by power smoothness alone. The comparison is instead organized around conductor architecture, insulation stress, machine and transformer utilization, conversion requirements, right-of-way utilization, and technological path dependence. A historical, commercial 6-phase demonstration showed that high-phase-order transmission was technically feasible and could improve corridor utilization. The paper then asks: if PE conversion and protection make phase count less costly, could \(m>3\) offer intrinsic advantages? Six such advantages are identified: modular decomposition into interleaved 3-phase groups, redundant control degrees of freedom, structured modal/fault analysis, increased corridor power density under field constraints, potentially higher natural loading and loadability, and enhanced harmonic/field cancellation. A companion derivation shows that phase count alone does not intrinsically reduce \(I^2R\) loss at fixed total conductor material and phase voltage. As a conditional conclusion, 3 phases are an unusually favorable historical optimum for electromechanical grids, but not a mathematically universal optimum for a future converter-dominated grid.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

A Finite-Sample Analysis of Quantile Temporal-Difference Learning

Zijie Cheng, Xiang Li, Yang Peng et al. (+1 more)

Quantile temporal-difference learning (QTD) is an effective method for learning return distributions through quantile approximation, yet its finite-time behavior remains poorly understood. Its update is nonlinear and nonsmooth, and the stability needed for a sharp convergence rate holds only near the target. We establish a global high-probability last-iterate guarantee for synchronous tabular QTD under general positive, nonincreasing step-size sequences and arbitrary initialization in the natural parameter range. For polynomially decaying step sizes with exponent $a\in(0,1)$, the last iterate converges to the target at rate $T^{-a/2}$ in the infinity norm, up to logarithmic and lower-order terms. A suitably tuned harmonic schedule recovers the $T^{-1/2}$ statistical rate up to logarithmic factors. For the $m$-quantile representation, its $\infty$-Wasserstein error scales as $\sqrt{m/T}$ up to logarithmic factors, matching the leading polynomial dependence on the quantile resolution and sample size of the corresponding model-based estimator. The proof uses a two-stage global-to-local argument. From arbitrary initialization, Bellman contraction and CDF monotonicity first bring the iterate close to the target, after which, a novel variance–drift matching argument sharpens the control of accumulated noise and local contraction reduces the remaining errors, yielding the sharp rate. Simulations verify the predicted polynomial decay and assess the finite-time entrance bound.
Read the full abstract

All authors Zijie Cheng, Xiang Li, Yang Peng, Zhihua Zhang

Artificial Intelligence

Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification

Jinghan Xu, Yikai Zhang, Aili Chen et al. (+3 more)

Agent harnesses shape how language-model agents use instructions, tools, and runtime components, but adapting these harnesses requires costly verification. Existing propose-and-verify methods typically score every candidate on a fixed task set, wasting rollouts on unrelated behaviors and allowing aggregate scores to obscure specific regressions. We introduce HarnessLens, a budget-aware framework for automated harness evolution. HarnessLens jointly explores the task space and user-configurable components, derives candidate modifications from execution trajectories, and selectively verifies each candidate on behavior-relevant tasks using an attributable-evidence gate. Across three agent harnesses and four benchmarks, HarnessLens improves average held-out performance by 7.6-13.6% while consuming substantially less evaluation budget than competing baselines. These results demonstrate that behavior-aware verification with explicit attribution enables more reliable and sample-efficient harness evolution under constrained interaction budgets. Our code is available at https://github.com/jhxu5214/HarnessLens.
Read the full abstract

All authors Jinghan Xu, Yikai Zhang, Aili Chen, Weiyuan Li, Jiaqing Liang, Deqing Yang

Computation and Language

Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit

Shuyi Fan, Boyuan Deng, Mengyu Xu et al. (+3 more)

LLM-judge audits assess bias by comparing ratings across matched conditions. Difference-in-differences designs take the rating difference between two candidate responses to each item and compare it across a manipulated attribute. Building on prior work on nonlinear difference-in-differences, we show in closed form that when ratings are bounded, a severity shift common to both responses produces an observed interaction whenever the scale bounds attenuate it unequally. We then report a pre-registered audit of 990 calls to a frozen pedagogy judge. The registered primary analysis did not detect an effect of a stated novice or advanced profile on scaffolding preference. The only nominally significant secondary interaction was on the productive-struggle sub-score ($+0.378$ points; $p = 0.002$). A post-hoc construction with zero differential preference reproduced 79 to 85% of this interaction using the observed severity shift and the scale floor alone. The observed interaction therefore does not identify differential preference on the latent scale.
Read the full abstract

All authors Shuyi Fan, Boyuan Deng, Mengyu Xu, Xinhong Xie, Chenyang Li, Hongyang Zhang

Machine Learning

QuantumBoostNet: Hybrid Classical-Quantum Cardiac View Identification

Mihai Udrescu-Milosav, Stefan-Alexandru Jura, Mihai Udrescu et al. (+1 more)

Accurate identification of the correct view or angle in cardiac ultrasound (echocardiogram) is critical for cardiologic imaging, precise anatomical interpretation, and reducing clinical errors. Most state-of-the-art classical models perform well on standard benchmarks but give suboptimal results in specialized medical imaging due to high noise levels. To address these challenges, this work proposes the hybrid classical-quantum architecture QuantumBoostNet, which combines a classical backbone with two heads: one classical and one quantum, a parametrized 10-qubit quantum circuit. The main contribution of this work is training in two stages, with an adaptive transition between heads controlled by a mixing parameter that monitors loss dynamics. Extensive experiments show that QuantumBoostNet outperforms the implemented baselines under matched training conditions. Statistically significant gains appear on FashionMNIST ($p_t=9.91\!\times\!10^{-6}$) and MNIST ($p_t=1.29\!\times\!10^{-5}$), with a less significant improvement on the echocardiography task ($p_t=0.0711$). The model also shows robustness to noise. These findings support continued development of hybrid classical-quantum models for specialized medical imaging applications.
Read the full abstract

All authors Mihai Udrescu-Milosav, Stefan-Alexandru Jura, Mihai Udrescu, Gerhard-Paul Diller

Graphics

Comparative Evaluation of 3D Reconstruction Methods for Immersive Visualization of Laboratory Objects

Brian De La Cruz, Aaron Y. Zhao, Maitrey Gramopadhye et al. (+4 more)

In this study, we examined whether current 3D reconstruction methods can support the creation of realistic holographic representations of laboratory objects for educational use. In this regard, we compared four approaches: photogrammetry, a neural radiance field (NeRF)-based method, Gaussian splatting, and LiDAR. These methods were used to generate holographic models of common laboratory items and their fidelity was evaluated by graduate students. Participants assessed the models for shape, color, texture, and visual defects using a repeated-measures design. Across objects, the NeRF-based method produced the most consistently high-fidelity representations, particularly for transparent, reflective, or low-texture items that were difficult to capture with other approaches. Shape and color were generally reproduced more successfully than texture, suggesting that some visual properties remain more challenging to represent accurately in educational holograms. Beyond identifying the strengths and limitations of each reconstruction method, the study demonstrates a practical workflow for creating immersive learning objects that may support pre-laboratory preparation, spatial reasoning, and student engagement in AR/MR-based educational environments. These findings offer design-relevant insights for educators and researchers developing immersive digital learning experiences.
Read the full abstract

All authors Brian De La Cruz, Aaron Y. Zhao, Maitrey Gramopadhye, Sawyer J. Lazar, Xianming Tan, Daniel Szafir, David S. Lawrence