User Embeddings are Superpositions of Interpretable Behavioral Modes
Jonathan Kozaczuk, Zheng Dong, Noyan Evirgen, Keivan Majidi, Eddie K. H. Ng, Chris Porter, Qi Zhao, Jia Geng 等 10 位作者
AI 速览：作者提出用户嵌入可视为可解释行为模式的稀疏叠加，并用稀疏自编码器事后恢复、命名和查询这些模式。
User embeddings are central components of modern recommendation, personalization, and behavioral modeling systems. Though these embeddings can compactly encode rich behavioral information, they are inherently dense and opaque, limiting interpretability. To address this gap, we argue that user embeddings can be understood as sparse superpositions of interpretable behavioral modes. This structure is directly predicted by generative models of user behavior for linear embeddings and extends approximately to deep-learning representations by the superposition hypothesis. Superimposed modes can naturally be recovered by sparse dictionary learning methods, such as sparse autoencoders (SAEs), and recovered modes can be automatically named and queried in natural language. We validate mode recovery against known ground truth on synthetic data, where SAEs recover modes better than classical sparse baselines, including on transformer-encoded embeddings. We then apply the method to classical and transformer-based user embeddings from two real-world datasets. We also show how the corresponding natural-language labels enable zero-shot audience retrieval and characterization over embeddings never trained on text. The framework is post-hoc and model-agnostic, requiring no modification to the upstream embedding system.
Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI
Xiaoqi Zhao, Youwei Pang, Kailai Zhou
AI 速览：作者通过对200篇论文中371幅动机图与框架图的视觉回顾和源约束修订实验，探讨生成式AI辅助科研图表设计时解释清晰度与视觉表达之间的权衡。
Scientific figures give research ideas a visual form through choices of abstraction, composition, and emphasis. Generative AI offers new ways to realize these choices, raising questions about explanatory clarity and purposeful visual expression. We examine these questions through a visual retrospective of 371 motivation and framework figures from 200 papers. The corpus comprises a quota-based main sample of 160 papers spanning four temporal periods and a separate purposive style-contrast sample of 40 papers. A single multimodal judge evaluates six dimensions of communication and design, with three repeated judgments per figure. We attempt source-constrained revisions of all 371 figures, of which 369 pass the recorded fidelity checks. Original-figure ratings show no uniform decline across periods. Revisions increase mean clarity ratings by 0.428 points and decrease aesthetic coherence ratings by 0.111 points on a five-point scale. Gains in the six-dimension average are larger for main-sample motivation figures than for frameworks. Case analyses show that added explanation can clarify comparisons while leaving typographic hierarchy and visual economy unresolved. These model-based findings support researcher-led design, with AI assisting exploration and authors retaining responsibility for explanatory purpose, composition, and scientific relationships. The accompanying atlas and evaluation records are available at https://ntu-ai4x.github.io/Rethinking_Figures/index_en.html.
David Yan, Le Xue, Forrest Huang, Qiuyi Zhang, Dustin Tran, Andrew M. Dai, Yinfei Yang
AI 速览：作者通过思维链分析方法和消融实验，考察带坐标接地的推理在哪些视觉推理任务中真正带来收益，并提出需要不可描述视觉指代的 BrickVision 基准。
Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual reasoning problems. However, the benefits and limitations of grounded reasoning are understudied. We study where and why grounded reasoning is most useful. To do so, we introduce a chain-of-thought analysis method to measure how much a model uses its outputted grounding in its thinking trace and perform a detailed ablation study of a grounded reasoning training recipe. We find that grounded reasoning improves counting but shows no significant gain over baselines without coordinate grounding across a wide range of spatial reasoning and perception benchmarks. Using several synthetic tasks, we show that grounded reasoning is most useful when a task requires undescribable references, which are visual concepts that are difficult to describe in language. However, we observe that many existing visual reasoning benchmarks are solvable with only describable text references. To close this gap, we introduce BrickVision, a new benchmark that requires undescribable visual references to solve.
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
Qile Jiang, George Em Karniadakis
AI 速览：提出让数百个低成本智能体在潜在空间中集群推理并通过传递 KV 缓存共享信息的进化搜索框架，以加速数学与科学计算问题的程序搜索。
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining high-scoring methods. However, the process is often slow because the LLM generates a long textual chain of thought for each round and must repeat this generation many times to maintain population diversity. We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches. Each swarm studies the problem from a different angle. A novelty filter keeps the most distinct agent ideas by directly measuring the distances between the agents' hidden state vectors. Crossover of ideas happens naturally in latent space, as a summarizer agent receives the combined KV caches of all swarm members. On 21 problems in mathematical discovery and scientific computing, SwarmEvolve gets the highest average score and needs a median of only 3 to 8 minutes to reach the best scores that other state-of-the-art frameworks reach in 60 minutes. On several problems, SwarmEvolve with Qwen3 8B improves on the solutions that AlphaEvolve first found with frontier LLMs. Our work shows that agent swarms that communicate in latent space offer a fast, low-cost approach to program search for scientific problems.
AI 速览：系统研究前向前向（Forward-Forward）算法中优良性函数的选择性与活动形状如何影响逐层学习，并提出基于超额峰度的 burstiness 目标。
The Forward-Forward (FF) algorithm trains networks layer-by-layer using a local "goodness function," yet the choice of activity statistic remains an important design question. We systematically study how selectivity and activity shape affect FF learning, introducing selective goodness functions based on top-$k$ and entmax-weighted energy alongside shape-sensitive objectives based on normalized higher-order moments. In particular, we propose burstiness goodness, a parameter-free, scale-invariant excess-kurtosis objective that rewards heavy-tailed activity patterns. Our study examines goodness functions together with activation and label-injection choices across six small-image datasets, and uses controlled experiments to isolate their effects. In validation-tuned, five-seed Fashion-MNIST experiments with matched ReLU activation, standard label injection, and per-layer scoring, burstiness improves accuracy from $73.2\pm0.9\%$ to $88.6\pm0.4\%$ over sum-of-squares. On CIFAR-10, burstiness improves block-local ResNet-18 accuracy from $28.9\pm0.5\%$ to $46.8\pm2.5\%$ under the same separate per-block label pathway. These results show that activity-shape statistics can provide effective local learning signals across the tested settings. Code is available at https://github.com/suayptalha/ff-selectivity-shape.
Scientist World: Grow a Research World for AI-Scientists
Taiming Lu, Sachin Konan, Zhuang Liu
AI 速览：作者提出将每篇论文转化为可执行环境，构建供 AI-Scientist 研究与训练的世界，并报告首批 1000 个已验证环境及初步评测与训练结果。
AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an executable environment. Our autonomous pipeline extracts each paper's open-ended research question and reproduces its proposed method as the baseline; an AI-Scientist entering the environment is evaluated against what the human authors achieved. We release the first 1,000 verified environments. With the world as an evaluation, we found that frontier AI-Scientists can already surpass the human researchers 74% of the time. As a record of how AI does science, it contains 6,400 hours of research traces, with every idea, experiment, failure, and success. As a training ground, we are able to raise (+158%) a small model to match frontier models in research ideation. At last, AI-Scientists' own world has arrived, grown from and growing with science itself.
AI 速览：作者提出 EgoGeneralist，将预训练视频生成器适配为统一处理动作条件第一人称视频生成、姿态估计与联合动作-视频生成的通用框架。
Modern video models possess strong visual priors, yet do not natively represent human action in metric 3D space. We present EgoGeneralist, which adapts pretrained video generators to unify action-conditioned egocentric video generation, pose estimation, and joint action-video generation. Our role-adaptive action renderer provides video-native representations for multidirectional action-video learning, making metric motion usable as both a spatial control signal and a recoverable generation target. Cross-stream action-video coupling establishes close correspondence between metric motion and visual dynamics through lightweight adaptation while preserving the pretrained visual prior. Together, these designs establish a generalist framework spanning five action-video tasks. Despite adaptation only on controlled laboratory recordings, EgoGeneralist generalizes to diverse unseen scenes and interactions with effective action control and visual quality, bridging pretrained visual knowledge and metric 3D human motion.
AI 速览：提出开源多智能体系统 HEMA，用大语言模型加36个领域工具支持多轮对话式家庭能源管理，并给出基于LLM模拟用户的评测框架。
Existing home energy management systems conceptualize occupants as passive recipients of energy information and control, which limits their ability to effectively support informed decision-making and sustained engagement. This paper presents Home Energy Management Assistant (HEMA), the first open-source, multi-agent system enabling sustained human-AI collaboration - multi-turn conversational interactions with preserved context - across diverse home energy management (HEM) tasks - from energy analysis and educational support to smart device control. HEMA combines large language model (LLM) reasoning capabilities with 36 purpose-built domain-specific tools through a three-layer architecture: a web-based conversational interface, a backend API server, and a multi-agent system. The system features three specialized agents - Analysis (energy consumption patterns and cost optimization), Knowledge (educational queries and rebate information), and Control (smart device management and scheduling) - coordinated through a self-consistency classifier that routes user queries using chain-of-thought reasoning. This architecture enables various energy analyses, adaptive explanations, and streamlined device control. HEMA also includes a comprehensive evaluation framework using an LLM-as-simulated-user methodology with 23 objective metrics across task performance, factual accuracy, interaction quality, and system efficiency, allowing systematic testing across diverse scenarios and user personas without requiring extensive human subject testing. Through demonstrations using real-world household energy consumption data, we show how HEMA supports informed decision-making and active engagement in HEM, highlighting its potential as a user-friendly, adaptable tool for residential deployment and as a research platform for HEM innovation.
SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
Jiaxi Liu, Keshu Wu, Weizhe Tang, Bofeng Cao, Sikai Chen, Xiaopeng Li, Steven T. Parker, Bin Ran
AI 速览：SAGE 将视觉语言模型（VLM）的轨迹作为对几何候选路径的偏好，在共享候选空间中分离路径构建、路径偏好与控制合规，以预测施工区临时交通管制下的通行路径。
Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path. Geometric predictors provide several plausible paths, yet selecting the one consistent with the temporary control remains difficult. We propose SAGE (Semantic-to-Action Grounded Execution), a read-decide-execute-check framework that separates path construction, path preference, and control compliance within a shared candidate space. The central idea is to use a vision-language model's (VLM's) trajectory as a preference over intact geometric candidates. A role-decoupled generator constructs the candidates, and rank fusion combines each candidate's geometric score with its agreement with the VLM trajectory. Supervision structured around the Manual on Uniform Traffic Control Devices (MUTCD) trains SAGE-VLM to state the lane status and hazard side before its passage decision and trajectory. The predicted hazard side enters image-space predicates derived from MUTCD provisions, which support a final intervention bounded in score and displacement. On 2,306 real-world ROADWork validation episodes, the candidates include a path within 10 px of the human demonstration in 87% of episodes, yet selection regret accounts for 53% of the geometric ranker's error. SAGE reduces average and final displacement errors by 8.3% and 12.0% relative to the ranker and hard-constraint violations by 37%. The trajectory opinion improves all four tested generator-selector combinations. SAGE is comparable to state-of-the-art VLM modules in accuracy, with a faster-responding VLM, and outperforms four other adapted driving VLMs in displacement error and safety measures. Project page: https://hhjj233.github.io/SAGE-page/.
AI 速览：作者比较半环注解数据库上一阶公式的两种基于解释的语义，并报告它们无法表达 monus 运算，因而无法刻画 SQL 语义。
Interpretations have been widely used in the study of provenance of queries on semiring-annotated databases. Here, we consider two different interpretation-based semantics for first-order formulas in negation normal form, namely, the canonical-interpretation semantics and the compatible-interpretation semantics. We show that the resulting query languages cannot express the monus operation on semiring-annotated relations, when the annotations come from the bag semiring or the tropical semiring or the fuzzy semiring. Consequently, the semantics of SQL cannot be captured using the interpretation-based semantics considered here.
AI 速览：作者提出 XStack 基准，用于评估智能体在 PyTorch/NVIDIA GPU 与 JAX/Google TPU 两大生态之间迁移完整机器学习仓库的能力。
ML code should run where researchers choose, not where it was first written. Today, machine learning code mainly lives in two ecosystems, PyTorch on NVIDIA GPUs and JAX on Google TPUs. Migrating repositories between them means building and testing across frameworks and hardware. This migration is (1) a practical need, since it unlocks different hardware for researchers, and (2) a natural benchmark: it involves different frameworks and hardware, covers whole repositories, and is long-horizon and challenging. We introduce XStack, a benchmark that evaluates agents on migrating ML repositories between these two ecosystems. Each agent receives a PyTorch repository and a clean TPU machine and must deliver a JAX repository. Its output passes if it meets our grading criteria, based on the source repository's published result, authenticated and calibrated by us. Migration by agents remains unreliable: Claude Opus 5 passes 75%, GPT-5.6-sol 45%, and every other agent at most 40%. XStack is a step toward freeing ML code from its ecosystem. We release XStack to make progress toward reliable migration across frameworks and hardware measurable.
Same Behavior, Different Mechanism: What Finite Experiments Can Certify About Integrated Information
Linqian Wu, Diaoxuan He
AI 速览：该文以整合信息论中的 φ 为严苛案例，研究机制层面的量能否从有限、部分、含噪干预中被识别、连续刻画并在有限数据下获得可证明的认证。
Interpretability, AI auditing and assessments of machine consciousness increasingly rest on mechanism-level quantities: functionals of a system's causal transition law that describe how it computes, not what it outputs. Experiments see that law only through finite, partial and noisy interventions. We ask when such a quantity is identifiable from an experiment's access, continuous in the mechanism and certifiable from finite data, and answer exactly for a deliberately demanding case - the integrated information $\varphi$ of integrated information theory - in stochastic networks of four and five units with known ground truth. Behavior can be silent: a recurrent and a feed-forward network with identical input-output laws at their response delay carry 0.28 and 0 bits, yet internal recordings separate them within 4-53 trials. Partial access can be just as blind: in our examples, units left out of a one-step recording impose precision floors of 0.30-1.02 bits that no sample size lowers, and in all-but-self parity networks, recordings of any length see several hidden units only through the product of their fidelities - a symmetry that one intervention broke in exact checks. The measure has sharp edges: because $\varphi$ selects a partition, and the cause and effect it specifies, by one criterion and reports another, infinitesimal changes of mechanism that cross an edge change it by 25-100% at 99% of the edges we found in random networks, and about 1% of surrogate models that fit interventional data almost perfectly misreport it by more than 20%. One-sided claims survive: the same data certify a lower bound on both sides of an edge, and we prove $\varphi>1.004$ bits throughout a 64-dimensional region of mechanisms and certify it from about $10^7$ controlled transitions with false-certificate probability at most $α$. Measurability is thus a design question with computable answers.
AI 速览：作者提出 FluxFlow，一种保守的像素空间流匹配框架，并构建 DESI–HST 真实地基—空间配准数据集，用于抑制天文超分辨率中的幻觉源。
Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by pixel sampling resolution and atmospheric seeing, which imposes a stochastic, spatially varying PSF that cannot be resolved through upsampling alone. Existing methods rely on synthetic training pairs that fail to capture real atmospheric statistics and are prone to either over-smoothed reconstructions or hallucination sources with no physical counterpart in the observed sky. We propose FluxFlow, a conservative pixel-space flow-matching framework that incorporates observation uncertainty and source-region importance weights during training, and a training-free Wiener-regularized test-time correction to suppress hallucination sources while preserving recovered detail. We further construct the DESI--HST Dataset, the large-scale real-world benchmark comprising 19,500 real co-registered ground-to-space image pairs with real atmospheric PSF variation. Experiments demonstrate that FluxFlow consistently outperforms existing baseline methods in both photometric and scientific accuracy. Project webpage: https://i2wm.github.io/fluxflow/.
Canonical Cut Hierarchy in Almost-Linear Time via Reduction to Max-Flow
Karthekeyan Chandrasekaran, Harshul Sagar
AI 速览：作者提出一种随机化几乎线性时间算法，通过归约到最大流来计算无向图中的规范割层级，并由此得到多个图参数与结构的快速算法。
The canonical cut hierarchy recursively partitions a graph along Tutte-Nash-Williams partitions, choosing the partition with the most number of parts at each step. We give a randomized almost linear-time algorithm for computing this hierarchy in undirected graphs with polynomially bounded capacities via reduction to max-flow. This yields randomized almost linear-time algorithms for computing partition connectivity, strength, both arboricity and fractional arboricity, both integral and fractional spanning tree packing numbers, and implicit representations of the principal partition sequence and a maximum fractional spanning tree packing.
Towards interpreting any residual stream direction by scaling activation inversion
Celeste De Schamphelaere, Juan J. Vazquez, Ari Spiesberger, Tomáš Gavenčiak, Gavin Leech, Euan Ong, Jiahai Feng
AI 速览：提出 Maximally-Activating Example Metamodels（MAEMs），用无标签强化学习把残差流方向映射为能强烈激活该方向的文本样例，以可验证的方式解读任意方向。
To interpret a direction in a language model's residual stream, we can look for text that strongly activates it. But when such text is found by scanning a corpus, it is limited to what that corpus contains. We develop Maximally-Activating Example Metamodels (MAEMs), language models which map residual stream directions from a subject model to text exemplars that strongly activate those directions. Our objective is to maximise the cosine similarity of a supplied residual stream direction with the activations of the text generated by the MAEM. This label-free RL objective helps to scale MAEMs on diverse sources of residual stream directions. Empirically, we find the resultant metamodel produces informative exemplars: a Qwen3.6-27B MAEM inverts held-out activations better than corpus search or a natural-language autoencoder (NLA), beats corpus search (at 10M tokens) on a majority of held-out languages/domains, and activates 89% of held-out SAE features. It also identifies concepts behind steering vectors about as well as NLAs, recovers the payloads of LoRA backdoors more often than corpus search, and can even verbalise some model workspace inner monologue. Unlike explanations produced by other metamodels (e.g. NLAs), MAEM exemplars can be verified with a forward pass on the subject model, making the MAEM objective a grounded alternative for scaling the training of metamodels.
AI 速览：提出OopsieRecover框架，通过溯因推理从少量纠正示范中推断失败意图，并以稠密空间表示和条件代价引导VLA策略泛化纠正行为。
Vision-Language-Action (VLA) models can perform a wide range of robotic manipulation tasks, but often fail during deployment. Teaching them to recover from these failures requires substantial corrective data: existing approaches learn to recover from failures by directly associating corrective actions with the observations in which they were demonstrated. For instance, DAgger-like fine-tuning can require tens to hundreds of interactions, yet the resulting policy may still fail to generalize the learned corrections beyond the demonstrated scenarios. We hypothesize that semantics can capture the underlying reasons for failures and their corrections, enabling policies to learn from only a handful of corrective demonstrations and generalize those corrections to novel objects, and scene variations. We propose OopsieRecover, a framework that uses abduction to infer the intent behind a small set of corrective demonstrations and encodes the inferred knowledge as dense spatial representations and conditional costs. These costs capture when a behavior is undesirable and steer the policy toward more desirable action regions. We experiment across 6 tasks and variations in object poses, scenes, and related tasks, and find that only a handful of corrective demonstrations can enable a VLA to overcome failures across a broad range of novel situations, without requiring new corrective data for each variation. Please refer to https://robin-lab.cs.utexas.edu/oopsierecover for videos.
Latent RL Priors for Data-Efficient Dexterous Manipulation
Yixiao Wang, Peiyi Chen, Mustafa Mukadam, Shreekant Gayaka, Masayoshi Tomizuka, Son Tran
AI 速览：提出两阶段框架 Latent RL Prior，将大规模特权强化学习学到的控制知识蒸馏为流匹配动作解码器，再仅用动作监督学习视觉接口，从而在少量视觉示范下实现数据高效的灵巧操作。
Learning dexterous manipulation from limited visual demonstrations is challenging because policies must acquire both perceptual grounding and precise control, while reinforcement learning (RL) in simulation can acquire rich control behaviors from large-scale interaction with privileged information. We introduce \textbf{Latent RL Prior}, a two-stage framework that reuses this control knowledge for data-efficient visual policy learning. During privileged pretraining, we distill large-scale RL rollouts into a flow-matching action decoder conditioned on proprioception and latent task context. During visual adaptation, we freeze the decoder and learn a visual interface that maps images to its latent context using action supervision alone, without privileged labels or latent targets. The same decoder can further be shared across arms by learning coordinated visual contexts for bimanual manipulation. Across three simulated tasks, our method outperforms full-parameter fine-tuning of $π_{0.5}$ and GR00T N1.7 in the low-data regime; on door lifting and bimanual assembly, it surpasses full-data baselines using $10\times$ and $5\times$ fewer demonstrations, respectively. Further analysis shows that direct visual-to-latent conditioning improves adaptation performance and training stability over routing visual predictions through the pretrained state encoder. Robustness to unseen mass variation and greater linear accessibility of contact-force information in decoder representations further provide evidence of retained RL-acquired control knowledge. Project website: https://yixiaowang7.github.io/latent-rl-prior-page/.
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore, William T. Freeman, Congyue Deng, Marin Soljačić
AI 速览：提出 SKILD，用尺度作为扩散动力学的显式坐标，在单一无条件框架内统一图像生成与连续超分辨率。
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce $\textbf{SKILD}$, a $\textbf{S}$cale-invariant $\textbf{K}$-Space $\textbf{I}$mage $\textbf{L}$earning $\textbf{D}$iffusion model that unifies generation and continuous super-resolution within a single unconditional framework. Both natural images and critical physical systems exhibit scale invariance, and we leverage it to design a forward process that attenuates image content from fine to coarse scales while injecting spectrum-matched Gaussian noise, making scale an explicit coordinate of the diffusion dynamics. The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: $\textit{no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor}$. Empirically, SKILD reaches FID $2.61$ and Inception Score $9.65$ on unconditional CIFAR-10, performs $2\times$--$8\times$ super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth.
Adversarial Training with Large Step Sizes: Implicit Bias, Optimization, and Sharpness
Yi Feng, Andrea Paudice
AI 速览：该论文研究确定性梯度下降在大恒定步长下对抗训练的动力学，分析隐式偏置、优化收敛与损失锐度的演化，并指出其与标准训练的三点关键差异。
Adversarial Training (AT) is an important method for improving model robustness. We study the dynamics of deterministic Gradient Descent (GD) in AT. Most existing works in this direction focus on the small or vanishing step sizes regime, where GD resembles a continuous-time flow. However, such step sizes can make training inefficient and are rarely used in practice. In this paper, we study the AT dynamics of GD with large constant step sizes. We first study GD in adversarial linear logistic regression, focusing on two aspects: where the model parameters converge (implicit bias) and how quickly the losses decrease (optimization). We then turn to neural networks training and study how the sharpness of losses evolve during AT. Our results advance the understanding of the behaviors of GD with large step sizes in AT and highlight three key differences from its behavior in Standard Training (ST): (i) the implicit bias gap between AT and ST, previously established only for small step sizes, persists for arbitrarily large constant step sizes, (ii) different from ST, there is no uniform rate of convergence for the optimization error in AT, and (iii) sharpness can exhibit two-stage dynamics that differ from the Edge-of-Stability behavior observed in ST.
Cognitive Tours: Making Understanding a Deliverable in AI-Assisted Development
Margaret-Anne Storey
AI 速览：提出基于Web原型的Cognitive Tours工具，通过连接用户需求、设计决策、代码、测试与开放问题的策展路径，缓解AI辅助开发中的认知债与意图债。
Generative AI and agentic coding are accelerating software development, leading to concerns about technical debt. But two less visible forms of debt, cognitive debt and intent debt, are emerging as key risks to software health. Cognitive debt is the absence or erosion of a team's shared understanding where no one can confidently explain how a system works or predict the impact of a change. Intent debt is the lack of clearly articulated goals, constraints, and rationale that explain what the system is for and guide how it should evolve. This paper presents Cognitive Tours, a tool designed to mitigate and repair cognitive and intent debt. Cognitive Tours is a web-based prototype for creating and following curated paths connecting user needs, design decisions, code, tests, and open questions. AI-assisted skills help audit existing waypoints and tours for possible problems or staleness and suggest candidates for new ones; humans decide what matters, verify relationships, and construct the narrative. This division of work deliberately preserves productive friction: the sensemaking involved in selecting, explaining, and revising a tour, which is intended to foster and share understanding. Our demonstration uses a tour of Cognitive Tours itself to introduce the tool and illustrate its design decisions and interaction mechanisms. A proposed evaluation agenda concludes the paper. A demo is available at https://cognitive-tours-demo.vercel.app/
AI 速览：该文确定了Tusnády问题在任意固定维度下的精确偏差阶，并将其应用于未知共同分布的两个独立样本的在线稀疏化问题。
We determine the sharp order of discrepancy in Tusnády's problem in every fixed dimension $d\ge 2$. The largest combinatorial discrepancy of $N$ points in $\mathbb{R}^d$ with respect to axis-parallel boxes is $Θ_d((\log N)^{d-1/2})$, extending Wei's planar result and matching Nikolov's upper bound. More strongly, with high probability, this lower bound holds simultaneously for every subset obtained by deleting at most a sufficiently small fixed fraction of a uniform $N$-point sample. We apply this geometric estimate to online thinning of two independent samples of size $n$ from an unknown common distribution, where observations must be kept or discarded upon arrival. For every fixed dimension $k\ge 1$ and expected deletion budget $ρn$, with $0<ρ<2$, we prove that the minimax expected prefix discrepancy over lower orthants is $Θ_{k,ρ}((\log n)^{k+1/2})$. In dimension one, the optimal terminal discrepancy is instead $Θ_ρ((\log\log n)^{3/2})$, giving a sharp separation between the prefix and terminal objectives. For $k\ge 2$, we obtain terminal bounds differing by a factor of $\log n$. The lower bounds are based on Gaussian small-ball estimates for box-incidence matrices, while the upper bounds use stationary Metropolis thinning and, in one dimension, a terminal cancellation procedure.
Unpacking the Compute Efficiency of Strong-to-Weak OPD against GRPO
Zeyu Leo Liu, Yang Li, Bo Pang, Emre Can Acikgoz, Xuan-Phi Nguyen, Anurag Koul, Srijan Bansal, Erik Nijkamp 等 10 位作者
AI 速览：系统比较反向KL在线策略蒸馏（OPD）与GRPO在达到目标准确率时所需训练FLOPs的差异，并揭示教师来源对OPD效率的关键影响。
On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher's per-token supervision. Does this dense signal reduce the training FLOPs needed to reach a target accuracy compared with reinforcement learning? We systematically compare vanilla reverse-KL OPD with Group Relative Policy Optimization (GRPO) across task difficulty, student and teacher size, domain, and optimization choices, measuring held-out accuracy against training FLOPs. With an external post-trained teacher, OPD generally loses to GRPO in accuracy per training FLOP at matched settings, even when the teacher is further trained with GRPO, and often suffers response-length inflation. Yet a different teacher changes the picture: when the teacher is the student's own GRPO checkpoint, OPD recovers that checkpoint's accuracy on math with $50\times$ fewer distillation FLOPs than GRPO needs to reach the same accuracy. Following the same teacher setting, we consistently observe this high efficiency with a larger student, on code, and in a second model family. On a single domain, however, the GRPO checkpoint is already the desired model, so distilling it adds to total compute. Across domains, separate GRPO checkpoints hold different capabilities, and no single checkpoint serves every domain. Multi-teacher OPD (DeepSeek-AI, 2026) consolidates per-domain GRPO experts into a single student that matches each expert's accuracy, with the distillation stage costing only 5.2% (on 2 domains) and 8.0% (on 4 domains) of the specialist training FLOPs. Counting specialist training and distillation together, this pipeline reaches joint GRPO's performance on the 2-domain mix with 42.0% fewer total FLOPs.
ReproBridge: Building Reproducibility into ML Research Artifacts
Yubo Wang, Rui Meng, Jaehyun Nam, Tomas Pfister, Jinsung Yoon
AI 速览：作者提出一套标准化可复现工件设计与智能体工作流 ReproBridge，并构建 ReproBridge-Bench 基准，报告精炼工件能提升编码智能体独立复现实验的成功率并降低 API 开销。
Reproducing machine learning experiments requires reconstructing procedures from information scattered across papers, released code, and supporting artifacts. For coding agents, reproduction success can therefore depend on their ability to fill in missing details, rather than on the released artifacts alone. We ask whether preserving recovered procedures and decisions improves subsequent independent reproduction. We define a standardized artifact design comprising a refined codebase, environment setup, experiment launchers, and a reproduction guide, and introduce ReproBridge, an agent workflow for constructing these refined reproducible artifacts. ReproBridge-Bench provides 1,029 tasks from 387 experiments across 36 papers, anchored by five human-verified reference scores per task. Agents attempt tasks in fresh sessions with raw code or refined artifacts; a separate Auditor checks execution evidence. Across four evaluated models, refined artifacts raise mean reproduction success from 76.4% to 92.6% and reduce downstream API spending by 19.7% on average. The cross-model success-rate spread narrows from 21.6 to 3.9 percentage points, with all four models achieving mean success rates above 90%. Removing any component reduces success in the ablation study, with the largest losses from code and environment removal. These results suggest that preserving execution knowledge helps even models with lower raw-code success reproduce experiments more reliably and at lower API cost.
VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding
Yu-Cheng Chou, Shihao Wang, Jin Huang, Chi-Pin Huang, Chiao-An Yang, Xianzhe Fan, Jing Wang, Zhiqi Li 等 19 位作者
AI 速览：VFlash 利用视觉基元的结构化特性，通过轻量级 drafter 一次前向预测整个基元坐标，以替代逐 token 自回归解码，从而提升视觉规划的精度与速度。
Models for physical AI tasks, such as robotics and autonomous driving, need not reason solely in language. They can use visual plans--points, bounding boxes, and trajectories--to represent spatial goals and anticipate motion. However, autoregressive vision-language models generate these plans one coordinate token at a time, making richer predictions increasingly costly. We introduce VFlash, a method for fast, accurate visual planning through Flash Primitive Decoding. VFlash exploits the known structure of visual primitives to predict their coordinates jointly, using a lightweight drafter that generates an entire primitive in one forward pass. The layout adapts to the primitive's type, dimensionality, and length, supporting compact boxes and long, variable-length trajectories. Crucially, spatial accuracy need not require reproducing an autoregressive model's exact token sequence. VFlash therefore trains on annotated primitives and directly accepts structurally valid predictions without target-token agreement. Across the evaluated 2D and 3D robot trajectory tasks, VFlash consistently reduces prediction errors relative to autoregressive decoding. Preliminary single-rollout measurements indicate approximately 25x faster generation for 3D point motion forecasting. A world action model conditioned on VFlash plans achieves 70.2% average success across four MolmoSpaces task suites, compared with 62.6% for the baseline.
Trainspotting: Learning Object-Centric 3D Reconstruction from Found Photos
Hanyu Chen, Noah Snavely
AI 速览：作者构建了来自 Wikimedia Commons 的、以物体为中心的多视角照片数据集 Trainspotting，并指出当前前馈重建模型在物体移动或多实体共享设计的场景下表现较差，而用该数据集微调 VGGT-Ω 可改善位姿、深度与几何重建。
State-of-the-art feedforward reconstruction models perform poorly on in-the-wild object-centric photo collections. They are trained largely on single-session object captures whose images vary in viewpoint while the object and its environment remain nearly fixed. Public photo archives contain a different form of multi-view data. They hold found photos of the same object or design: photos taken independently by many people across years, environments, cameras, and sometimes physical units. In this work, we introduce Trainspotting, a dataset of 12,068 objects and 311,886 photos from Wikimedia Commons. We reconstruct each object to recover camera poses, multi-view stereo depth, and object masks. We categorize the objects into three regimes: objects fixed at one site, objects that move between sites, and designs shared by many physical units. Evaluating recent feedforward reconstruction models on Trainspotting shows that they fail most severely in the last two regimes. Fine-tuning VGGT-$Ω$ on Trainspotting significantly improves camera pose, depth, and 3D geometry on held-out objects. We observe similar improvements on the independent NAVI in-the-wild benchmark, which contains photos of each object in different environments. Performance on conventional benchmarks remains largely unchanged.
Chaithanya Rayudu, Takahiro Misawa, Andrew Zhao, Jun Takahashi
AI 速览：作者证明了一类广泛相互作用的费米子模型配分函数的李-杨零点不存在定理，并据此给出估计基态能量的可证明高效量子算法。
Lee-Yang theorems are a powerful tool for studying many-body systems, with applications ranging from analyzing phase transitions to proving the efficiency of certain classical and quantum algorithms. In this work, we prove a Lee-Yang zero-freeness theorem for the partition function of a broad class of interacting fermion models, implying the existence of a provably efficient quantum algorithm for estimating their ground-state energies. This class includes several well-known models such as the attractive Hubbard model, repulsive Hubbard model on bipartite graphs, and the interacting Hofstadter model. Our results also rigorously establish the nonexistence of phase transitions in these models in the presence of a nonzero local external field.
Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale
Edesio Alcobaça, Kevin Rossell, Aman Gupta, Shao Tang, Jiwoo Hong, Pabel Carrillo-Mendoza, Wanderson Conceição Ferreira, Alvaro Tedeschi 等 16 位作者
AI 速览：提出一种假设驱动的仿真工作流，在部署前用合成客户与模拟工具输出筛选客服AI智能体，并在Nubank真实业务中验证其与生产表现的相关性。
Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Improving these agents, especially in regulated industries, is difficult: they must detect intent, follow complex operational policies and use tools reliably. Manual end-to-end testing offers limited coverage, while live experiments expose customers to failures that can erode trust. We present a hypothesis-driven simulation workflow for screening candidate CX agents before deployment. Synthetic customers react to agent responses and simulated tool outputs enable multi-step agentic workflows without invoking production backends. We use the Snowglobe simulator on Nubank's Card Delivery agent and its expanded successor, Card Management - Nubank's highest-volume chat-support agent in Brazil. Across 4 deployed versions, simulated and production version-level binary evaluator scores show high correlation. Simulation-guided iteration increased transactional net promoter score (tNPS) by 36.69 points in a live A/B test. We also screened open-weight configurations in over 16,000 simulated conversations. In a subsequent live A/B test, the selected model increased self-service rate (SSR) by 8.82 percentage points to the highest level observed at Nubank, with no statistically significant change in tNPS. Simulation made broad exploration of models, reasoning settings, and prompts feasible without customer exposure, enabling production improvements that would have been impractical to pursue through live experimentation alone.
A Hidden Markov Preference Model for Online Prediction of Adversary Actions
Angel Daruna, Michael Cogswell, Tixiao Shan, Yi Yao, Han-Pang Chiu, Ajay Divakaran
AI 速览：作者提出一种隐马尔可夫偏好模型，用潜在行为机制状态和可行性掩码的动作树，在线预测攻击者的下一步动作。
A defender anticipating an attacker needs a probability distribution over the attacker's next action from information available before that action occurs. Two structures complicate this: the attacker's behavioral regime persists and can switch within an episode, and each action combines an operation with state-dependent arguments whose feasible values change over time. We capture both with a hidden Markov model whose latent state is the active regime and whose regime-conditioned action law is defined on a feasibility-masked tree of executable actions. The same likelihood forms the next-action distribution and updates the regime belief once the action is seen, and a partially observed prefix contributes its resolved local factors. Estimation separates into convex logistic fits that Baum-Welch reuses when regimes are unlabeled. We derive a reach-weighted nodewise KL expression for regime information, a sequence-wise log-loss bound for switching regime paths, and a uniform fallback guarantee. On the CAGE 2 cyber defense benchmark the filtered latent state is worth 0.8 nats per step, and after a controller switch the loss begins to fall in three steps against ten for a recurrent baseline.
Polynomial-time classical simulation of boson and fermion sampling under thermal loss
Armando Angrisani, Hela Mhiri
AI 速览：作者提出统一框架，证明在任意固定非零总损耗率下，若干玻色子与费米子采样任务可被多项式时间经典模拟。
Sampling experiments are a leading approach to demonstrating quantum computational advantage, yet their robustness to experimental noise is not completely understood. We develop a common framework for classical simulation of boson and fermion sampling under thermal loss, including pure loss. For Fock-state boson sampling, Gaussian boson sampling with fixed uniform squeezing, and fermion sampling with magic inputs, we obtain polynomial-time sampling at inverse-polynomial total variation error, for any fixed nonzero overall loss rate, and with high probability over Haar-random interferometers. A milder flatness assumption on the ideal output distribution suffices for quasipolynomial-time simulation without Haar randomness. With constant thermal loss per layer, the same flatness assumption gives polynomial-time simulation at logarithmic depth. Our bounds for Fock-state boson sampling cover both dilute and saturated regimes and become stronger near full input filling: when only a bounded number of input modes are empty, the noisy output for Haar-random interferometers converges, as the number of modes grows, to a distribution independent of the interferometer.
Souffleur: A Glanceable Display for Mobile Voice Conversations
Anton Wolter, William Benjamin, Niklas Elmqvist
AI 速览：作者设计并评估了一种移动优先、语音驱动、可一瞥获取要点的显示界面 Souffleur，用于帮助用户在上下文切换后继续语音对话。
The speech capabilities of mobile devices have grown, but their displays still rely on a text-based chat. When resuming a voice chat after a context switch, the last messages may not convey the key points of the conversation. Autobiographical use and sessions with external participants led to design goals for a mobile-first, speech-driven, glanceable display that helps users continue their reasoning from where they left off. We implement these goals in Souffleur and evaluate it in a between-subjects study with 48 participants. Compared with a conventional chat transcript, we found no reliable difference in how easily participants followed and resumed short voice conversations, nor in effort, attention or recall, although Souffleur reduces the conversation to a few short phrases.