AI 速览：提出 TASC 基准，评估 LLM 助手在对话中能否识别并应用未明说的时间相关约束来调整建议。
Large language model (LLM) assistants increasingly help users with everyday activities that involve time-dependent constraints. However, users may not mention these constraints in later requests, requiring assistants to recognize and adjust their advice accordingly. To evaluate such capability, we introduce TASC (Temporal Action Safety in Conversation), a benchmark that evaluates whether LLMs apply time-dependent constraints when responding to conversational requests. TASC consists of 3,418 inputs derived from 128 templates, along with a separate set of 33 scenarios designed to compare models' ability to calculate elapsed time with their ability to apply that information. Across 13 models, assistants account for time-dependent constraints in only 30.5% of cases where the proposed action violates a rule, while rarely warning users unnecessarily. More importantly, models fail to apply these constraints in 62.1% of cases despite correctly calculating the elapsed time. Explicitly providing the timing resolves only about half of these failures, revealing a gap between temporal reasoning and its application in conversational advice.
AI 速览：提出上下文感知的自回归图像生成框架，让模型依据全局上下文与当前局部信息动态决定下一个 token 的位置，而非固定或随机顺序。
Autoregressive image generation has recently emerged as a competitive visual generation paradigm, yet its generation order is often predefined or heuristic, such as next-patch prediction, random-order prediction, or one-step generation for specific scales. We observe that these strategies can cause models to overlook important structural dependencies in images, thereby limiting both structural robustness and reasoning capability. In this work, we propose a context-aware autoregressive generation framework, where the model dynamically determines the next token location based on global context and current local information. Rather than following a fixed or random order, our method allows the generation process to adapt to image structure and semantic dependencies. Extensive experiments show that context-aware generation significantly improves structural robustness across different image AR paradigms, including masked autoregressive and scale-wise autoregressive models. Beyond quantitative improvements, we further observe emerging reasoning properties: the model can better understand complex semantic instructions and generate images that more faithfully follow the given guidance. These findings suggest that generation order is a critical yet underexplored factor in image autoregressive modeling, and that context-aware decoding can unlock stronger reasoning-aware visual generation capabilities. Code is available at https://github.com/Hpesojyjx/Saccades-AR.
Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token
Tommy He, Thomas Jiralerspong
AI 速览：作者提出并训练上下文—答案元模型，用阅读上下文时产生的激活序列预测答案激活的均值池化结果及其分布，从而在生成首个答案 token 前对模型行为做可扩展预测。
Under stochastic decoding, a single context can elicit many different answers from a language model. Characterizing this variation typically requires many expensive autoregressive rollouts, each revealing only one realization. We ask whether the activations produced while reading the context can directly forecast the model's rollout activations. We train context--answer metamodels that map a context activation sequence to point or distribution forecasts of mean-pooled answer activations. We find that (i) the four metamodel families we study forecast mean-pooled answer activations with high fidelity, and the distribution metamodels also capture rollout variability; (ii) performance improves as the training set grows to 500,000 prompts, and the metamodels generalize zero-shot to out-of-domain datasets; (iii) their forecasts retain behavior-predictive signal; and (iv) context activations from Qwen2.5 predict mean-pooled answer activations from Qwen3.5 and Gemma 4, suggesting that activation forecasts can transfer across models. Together, these results suggest that context activation traces can support scalable forecasts of behaviors in LLM answers before the first answer token is generated.
AI 速览：作者提出 LooM，在因果编码器-解码器中只循环解码器层，并让每个 token 的 KV 只在首次访问时写入，从而在缓存不随循环次数增长的前提下，把有效深度变成部署时可选的预算。
Looped Transformers increase effective depth by re-executing shared layers, but three limitations hinder their adoption: memory grows with the loop count, compute can only be adjusted in whole-block steps, and the loop count is hard to change after training. We propose LooM (Loop-invariant Memory), which addresses each in turn. In a causal encoder-decoder (CED), LooM loops only the decoder layers after the first, which read a global memory written once per token, and each of them publishes the key-value (KV) entry for a token only on its first visit, so the cache does not grow with the loop count. These layers loop independently, providing every budget from 3 to 21 layer executions per token, and one model trained on randomly sampled budgets covers all of them without a router. With enough loops, LooM outperforms a single-pass baseline trained on the same data on language modeling, zero-shot accuracy and long-context perplexity, while using the same cache size. Our analysis further shows that the training budget distribution decides what extra depth buys. These results suggest that a CED is a natural place to loop: memory is written once, and depth becomes a budget chosen at deployment.
Coexistence-Aware Antenna Tilt and Resource Allocation for Cellular-Connected UAV Corridors
Tarun Singh Rawat, Pradyumna Kumar Bishoyi
AI 速览：针对蜂窝连接无人机走廊与地面用户共存场景，联合优化天线倾角与PRB分配，在走廊速率和地面用户时延约束下最大化地面用户和速率。
Cellular-connected UAV corridors reuse terrestrial infrastructure to provide predictable aerial connectivity, but coexistence with ground users (GUEs) creates competing demands on antenna tilt and physical resource blocks (PRBs). Prior work optimizes tilt for signal quality alone and does not address joint tilt-PRB planning under corridor rate and GUE delay constraints, nor the allocation policy needed when combined resource claims exceed the PRB budget. We address both gaps by formulating a joint antenna-tilt and PRB-allocation problem that maximizes GUE sum-log-rate subject to a minimum UAV corridor rate and an $ M/G/1$-based GUE mean-delay bound. We decompose the problem into two subproblems: antenna tilts are adapted via projected gradient ascent, while PRB allocation follows a techno-economic approach. Under resource scarcity, we cast the PRB scarcity as a bankruptcy problem and apply the weighted Talmud rule to balance GUE and UAV claims. Simulation results demonstrate that relaxing the GUE delay bound consistently reduces UAV rate dissatisfaction under the proposed allocation.
Remi Denton, Aida Davani, Cynthia L Bennett, Michael Madaio, Roma Patel, Himabindu Lakkaraju
AI 速览：作者指出当前生成式AI对齐依赖短视范式、只优化即时对话满意度，忽视长期人机交互的外部性，并倡议转向长时程对齐。
Current generative AI alignment relies on a myopic paradigm that prioritizes immediate conversational satisfaction. By relying on short-horizon feedback, this approach ignores the profound, longitudinal externalities of persistent human-AI interaction, which can lead to adverse outcomes such as cognitive atrophy, social erosion, and diminished human agency. To address this, we propose a paradigm shift toward long-horizon alignment that accounts for how AI reshapes human experience over time. To this end, we map the tensions between near-term utility and long-term costs of AI use across four facets of human well-being to reveal outcomes that current reward models fail to capture. Ultimately, we advocate for moving beyond simple preference optimization toward alignment strategies that actively foster long-term human well-being by navigating these complex temporal scales.
We present a toolchain for development of ML models on AWS EC2 F2 cloud FPGA infrastructure from high-level language, implementing a complete Vitis HLS to HDK bridge to AFI workflow that has been absent from the academic literature despite eight years of AWS FPGA availability. We introduce a four-level methodology (FP32 PyTorch, bit-accurate quantized Python, HLS C-simulation, physical FPGA) to aid in localizing errors, including FPGA-specific circuit errors. Together these tools allow coding agents to effectively implement FPGA designs from user directions, testing and debugging as needed. We document the deployment workflow, timing closure strategies, and practical HLS engineering decisions that proved crucial. We validate using TinyBERT fine-tuned for address Named Entity Recognition, implementing the embedding layer and the first of four encoder layers on the FPGA hardware. Our implementation streams weights from host DRAM, yielding poor performance compared to CPU/GPU implementations; we discuss forward paths.
Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUs
Gagik Amirkhanyan, Nuojin Cheng
AI 速览：作者提出SLA，通过加宽键维度、分组衰减门和单核融合分块求解，使门控Delta线性注意力更适配TPU的宽脉动矩阵单元，并报告了相对KDA内核与预训练的训练加速。
Gated-delta linear attention layers such as Gated DeltaNet (GDN), Kimi Delta Attention (KDA), and GDN-2 are tuned for GPUs, where small tensor-core tiles and fast vector registers make per-channel decay rescaling and sequential in-block solves cheap. On Google TPUs, which concentrate compute in wide $256 \times 256$ systolic matrix units backed by a slower vector unit, porting these layers directly leaves half of each matrix tile empty and bottlenecks on vector operations. We present \textbf{Systolic Linear Attention (SLA)}, which reshapes gated delta attention around the matrix unit by widening keys to $256$ with grouped value heads, grouping decay gates into four $64$-channel tiles, and computing the chunk solve entirely with block matrix products in a single fused kernel. On TPU v7x, a full \texttt{SLA-R4} layer runs $1.6\times$--$2.5\times$ faster than the open-source Tokamax KDA kernel ($1.4\times$--$2.4\times$ with exact chunk inversion), driven primarily by head sharing and kernel fusion. Across a $2{,}048$-chip TPU v7x pre-training study of sparse Mixture-of-Experts (MoE) models from $6.5\text{B}$ to $63.1\text{B}$ parameters, SLA trains $11\%$--$24\%$ faster than KDA at similar perplexity, and reaches slightly lower perplexity than KDA in smaller matched-seed runs.
Learning POMDP World Models from Observations with Language-Model Priors
Valentin Six, Frederik Panse, Mathis Fajeau, Lancelot Da Costa, Mridul Sharma, Alfonso Amayuelas, Tim Z. Xiao, David Hyland 等 10 位作者
AI 速览：提出Pinductor，用大语言模型从少量观测-动作轨迹中提出并迭代精炼POMDP候选模型，以信念似然为目标，从而减少环境交互。
Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model of how that environment works. Partially-observable Markov decision processes (POMDPs) provide a flexible modeling class for such internal world models, but learning them from observation-action trajectories alone is challenging and typically requires extensive environment interaction. We ask whether language-model priors can reduce costly interaction by leveraging prior knowledge, and introduce Pinductor (POMDP-inductor): an LLM proposes candidate POMDP models from a few observation-action trajectories and iteratively refines them to optimize a belief-based likelihood score. Despite relying on strictly less information, Pinductor achieves comparable performance and sample efficiency to LLM-based POMDP learning methods with privileged access to hidden states. Moreover, it is up to 330 times more sample-efficient than standard POMDP baselines such as DreamerV3, at comparable computational cost. Further results show that performance scales with LLM capability and degrades gracefully as semantic information about the environment is withheld. Together, these results position language-model priors as a practical tool for sample-efficient world-model learning under partial observability, and a step toward generalist agents in real-world environments. Code: https://github.com/atomresearch/pinductor.
Stabilizing On-Policy Targeted Guidance in Agentic Reinforcement Learning
Kevin Frans, Alexander M Rush, Sergey Levine, Pieter Abbeel, Ashvin Nair
AI 速览：作者提出并分析“定向引导”框架，通过同策略自蒸馏从逐轮文本反馈中学习，并在智能体多轮软件工程环境中探索如何稳定训练且不损害基线RL性能。
Naive on-policy RL is often bottlenecked by the capabilities of the base model --- insufficient coverage can result in an inability to learn from certain rewards. At the same time, rewards in modern post-training systems often come from rich textual sources, e.g. judge models with a rubric of criteria. Can we utilize such structures to provide a rich directional signal that enables improving on otherwise difficult to optimize rewards? In this work, we examine a framework we refer to as targeted guidance that learns from per-turn textual feedback via an on-policy self-distillation objective. Our focus is not only on directly improving hard-to-optimize behaviors, but on how to do so throughout the training process without degrading baseline RL performance. Over a range of settings across an agentic multi-turn software engineering environment, we find success by combining targeted self-distillation with a per-criteria RL reward, and by limiting feedback to turns where the policy specifically fails. We further examine the design choices that lead to stable entropy and reduce oscillatory behavior throughout training.
Rules, Traces and Routing Statistics: Training and Calibration Data for Open Models on ARC-AGI-2
Nguyen Minh Thang, Trinh Thi Phuong
AI 速览：研究在四块 L4 GPU、12 小时离线约束下，哪类训练与校准数据能帮助三个开放模型解决 ARC-AGI-2 任务。
We study which training and calibration data help three open models solve ARC-AGI-2 tasks when the solver runs offline on four L4 GPUs for at most 12 hours. We compare data offline on public tasks and report 189 runs on the 120 hidden semi-private tasks. For the NVARC Qwen3-4B grid model, we built a corpus of 12,000 executable rules in a typed language and 95,993 tasks; a rule is admitted only if its behaviour on a fixed probe set differs from that of every admitted rule, and a task only if its pairs refute a shortlist of nearest competing rules and defeat 12 shortcut solvers. Continued fine-tuning on 1,920 real task records with revised four-GPU scheduling raised the semi-private score from 28.96 (mean of the released model) to 33.06 (mean of five runs, best 34.86); no checkpoint trained with synthetic tasks, even all 95,993 of them, improved on the real-task model. For the Qwen3.8-27B reasoning model, we fine-tuned on 1,036 of its own reasoning traces with correct final answers and compared sets that add traces of other models and synthetic tasks. With an inference procedure built around the model (a thinking cap enforced in the serving engine, a Python program checked on the demonstrations after each answer, a long first attempt per input), the score rose from 26.81 to 44.03, the level the ARC Prize Foundation measured for the base model without a time limit (42.36); most of the gain came from the inference procedure. For the Qwen3.8-Flash-Next mixture-of-experts model (125B parameters, 6B active), GPU memory limited concurrency. Pruning from 512 to 384 experts per layer by router-weighted activation saliency grew the key-value cache from 0.55M to 1.39M tokens; a 296-expert list adapted with ARC routing statistics, keeping experts for program tokens, plus an FP8 indexer cache, reached 1.96M. With a tool that checks programs, the model scored 56.67, our best result.
CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
Austin Tudor David Andrews, Liam Wilkinson, Jamie Heagerty, Harry Coppock, Jakob Nicolaus Foerster, Rui Ponte Costa
AI 速览：作者提出开源基准 CivBench，通过 MCP 在《文明VI》中评测语言模型智能体的长时程、工具中介行为，并提出 PMR 与 RAG@10 两个接口级指标。
We present CivBench, an open-source benchmark for evaluating language model agents in long-horizon, tool-mediated environments through the Model Context Protocol (MCP). A single episode can span over 300 turns and produces thousands of tool calls over a large action space, requiring sustained planning, state monitoring, and execution under partial observability. The environment exposes 76 MCP tools and a deterministic narration layer that retrieves and formats game state as structured text. We use CivBench to characterise agent behaviour across four model families in 23 admissible runs. The sample is a pilot, not a model ranking: aggregate outcomes do not reliably discriminate models at this scale. Instead, we introduce two interface-level metrics that the environment makes measurable: Proactive Monitoring Rate (PMR), capturing whether agents actively query latent strategic state, and RAG@10, capturing whether commitments stated in structured planning reflections are executed within ten subsequent turns. Across runs we observe two consistent patterns under a shared playbook protocol. Agents under-monitor strategically relevant state that is available but requires explicit querying: despite playbook guidance to query victory progress every 20 turns, agents do so only every 30-75 turns, and in 8 of 20 detectable defeats they failed to query within the 20-turn warning window before game end. Agents also frequently fail to execute near-term commitments stated in their own planning reflections (RAG@10 between 48.2% and 65.8% across models). Both patterns arise despite tool access and explicit guidance, and we interpret them as deviations under instruction rather than absences of capability. We release the environment, scenarios, logs, metrics, and analysis pipeline at https://github.com/lmwilki/civ6-mcp.
ESS-Flow: Training-free guidance as Bayesian inference in source space
Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund, Fredrik Lindsten
AI 速览：ESS-Flow 利用流模型源分布的高斯先验，在源空间用椭圆切片采样做无梯度贝叶斯推断，实现预训练流模型的条件生成。
Guiding pretrained flow-based generative models for conditional generation or to produce samples with desired target properties enables solving diverse tasks without retraining on paired data. We present ESS-Flow, a gradient-free method that leverages the Gaussian prior of the source distribution in flow-based models to perform Bayesian inference directly in the source space using elliptical slice sampling. ESS-Flow only requires forward passes through the generative model and observation process, making it applicable even when gradients are unavailable, such as with non-differentiable simulation-based observations or quantization in the generation process. We demonstrate its effectiveness on scientific applications including generating materials with target properties, protein backbone structures with improved designability, and synthesizable, drug-like molecules.
Kimball's Data Warehouse Architecture: Evaluating the Challenges of Conformed Data against the Inmon Model
Júlio Rocha, Salviano Soares, António Valente
AI 速览：该文围绕 Kimball 以一致性维度为核心的数据总线架构与 Inmon 的 hub-and-spoke 架构展开比较，重点讨论一致性数据面临的挑战。
In recent decades, driven by rapid data growth, organisations have faced the need to restructure their storage frameworks to efficiently handle queries requested by employees through available enterprise applications. Investigating this need involves examining the classic approaches of William H. Inmon, widely known as the father of Data Warehousing, and Ralph Kimball. Although both shared the same core concerns, Kimball later suggested an alternative architecture focused primarily on user needs. According to Ariyachandra and Watson, Inmon's "hub-and-spoke" architecture and Kimball's data bus framework featuring conformed dimensions stand out among alternative approaches. A comparison across these architectures highlights four key aspects: Information Quality, System Quality, Individual Impacts, and Organisational Impacts. Although Kimball and Inmon proposed contrasting solutions, they did not view each other as rivals. For instance, in one of the editions of the book "The Data Warehouse Toolkit", published by Kimball in 1996, the back cover features a note by Inmon stating that it is "one of the definitive books of our industry. If you take time to read only one professional book, make it this book.
GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes
Nuno Batista, Gabriel Falcao, Penousal Machado
AI 速览：作者提出首个用于量子码设计的生成流网络GFlowQEC，在有限昂贵评估预算下比并行回火和监督筛选找到更多新的高分量子LDPC码。
Choosing a quantum error-correcting code for a real device means scoring candidates with circuit-level simulations so slow that only a few hundred can be run. So every evaluation counts, and a search is judged by how many good codes it finds per paid evaluation. Quantum LDPC codes built from a few group elements protect many logical qubits, but good ones are rare in a huge space. We introduce GFlowQEC, to our knowledge the first generative flow network (GFlowNet) for quantum code design. It builds a code one group element at a time and learns to propose codes in proportion to a power of their score. We train it once on scores from earlier searches, freeze it, and let it propose lifted-product codes with 180 physical qubits, scored by their distances. Ranking ten of its draws per paid call, it finds more than twice as many new top-scoring codes (inequivalent to any it was trained on) as tuned parallel tempering, even when tempering starts from GFlowQEC's training codes. It finds more than three and a half times as many as a supervised screen ranking ten random candidates per call. When both rank a hundred, the screen beats GFlowQEC, and does best ranking GFlowQEC's draws. Soft Q-learning, which shares the GFlowNet's optimal policy, does as well at one noise bias and better at the other, so the gain does not depend on the GFlowNet's training loss. Trained proposers can make a budget of expensive evaluations go further when good codes are rare.
Linear-time erasure recovery for quantum expander codes
Anirudh Krishna, Christopher A. Pattison
AI 速览：作者提出 Small-Set-Peeling 算法，将经典 Peeling 擦除解码器推广到量子扩展码，并声称可在码的设计距离 D 下以线性时间纠正至多 D-1 个擦除。
Erasures are used to model faults at a subset of known locations in various platforms used to construct fault-tolerant quantum computers. Beyond the utility in erasure recovery, efficient decoders for erasures are useful to both understand error decoders and as a subroutine for error decoding. Classical expander codes, which belong to the family of low-density parity-check (LDPC) codes, can be equipped with the Peeling decoder which works in linear time. Our main result is the algorithm Small-Set-Peeling, a quantum generalization of the classical Peeling decoder for erasures, that applies to quantum expander codes (Tillich, Zémor, IEEE T-IT 2013; Leverrier, Tillich, Zémor, FOCS 2015). This decoder can correct up to $D-1$ erasures, where $D$ is the (design) distance of the code and, importantly, is the first decoder that is guaranteed to do so in linear time. Combining with the erasure-conversion algorithm Small-Set-Find (Krishna, Livni-Navon, Wootters, SODA 2024), our result also implies the existence of a novel graph-local linear-time decoder for Pauli errors.
Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
Juncheng Ma, Jiaxin Li, Jiankai Tu, Bo Liang, Guodong Lv, Yufan Deng, Junzhe Tang, Liangzhu Yang 等 31 位作者
AI 速览：提出首个全开放的第一人称人类视频预训练扩展方案，构建5万小时带标注语料并探索人类—机器人联合预训练的世界—动作模型。
Egocentric human video offers a scalable source of manipulation priors for robot learning, yet translating raw data scale into generalizable robot policies demands rigorous data curation and training recipes. We introduce Open-HumanScale, the first fully open recipe for scaling egocentric pretraining to 50,000 hours, anchored by Open-HumanScale-50K---a curated egocentric video corpus densely annotated with hand motion and natural language. Leveraging this corpus, we systematically investigate pure human pretraining via closed-loop simulation evaluations and uncover an empirical log-linear scaling law linking pretraining data hours to downstream robot success rates. Grounded in these findings, we develop HumanWAM-Vanilla, a world--action model pretrained exclusively on 50k hours of egocentric human video. Upon robot post-training, HumanWAM-Vanilla reaches 92.08% success on RoboTwin 2.0 Clean2Clean and 68.88% on Clean2Random, alongside a 14.17% mean success rate and a 19.00 mean progress score on RoboDojo. To push the capability frontier further, we explore joint human--robot pretraining with HumanWAM-Goal, a visual-goal-conditioned world--action model. Hybrid data scaling unlocks broad zero-shot generalization across both simulation and physical benchmarks, propelling post-trained RoboTwin 2.0 performance to new state-of-the-art levels: 92.70% on Clean2Clean and a substantial leap to 84.60% on Clean2Random. On physical robots, HumanWAM-Goal further exhibits emergent embodied in-context learning, dynamically adapting its manipulation behavior to unseen visual goals without parameter updates. To support reproducible scaling research in embodied AI, we open-source the Open-HumanScale-50K corpus, data curation and pretraining pipelines, alongside the pretrained and post-trained HumanWAM checkpoints, inference code, and simulation evaluation suites.
Boxicity of Power Graphs of Finite Nilpotent Groups
L. Sunil Chandran, Jinia Ghosh, Suraj Kumar Sahoo
AI 速览：该论文确定了有限幂零群幂图的精确盒度，并部分回答了关于任意有限群幂图盒度的公开问题。
The \textit{boxicity} of an undirected graph $Γ$, denoted as $\operatorname{box}(Γ)$, is the smallest non-negative integer $d$ such that $Γ$ can be represented as the intersection graph of axis-parallel rectangular boxes in $\mathbb{R}^d$. The \emph{power graph} of a group $G$, denoted as $\operatorname{Pow}(G)$, is an undirected graph whose vertex set is the group itself, with two elements being adjacent if one is a power of the other. We determine the exact boxicity of power graphs of finite nilpotent groups. For a cyclic group of order $n=\prod_{i=1}^{r}p_i^{e_i}>1$, where the $p_i$ are distinct primes, we prove that its power graph has boxicity $\sum_{i=1}^{r}e_i-\max_i e_i$. For a finite nilpotent group $G$, let the number of noncyclic odd Sylow subgroups be denoted by $t(G)$. If $G$ has odd order or if $G$ has a cyclic Sylow $2$-subgroup, then $\operatorname{box}(\operatorname{Pow}(G))=\operatorname{box}(\operatorname{Pow}(\mathbb{Z}_{\operatorname{exp}(G)}))+t(G)$, where $\operatorname{exp}(G)$ denotes the \emph{exponent} of a group $G$. When the Sylow $2$-subgroup is noncyclic, and the odd part is nontrivial, the boxicity equals this value or one more, and we characterise precisely when each of these values is attained. The boxicity of power graphs of arbitrary finite groups and the exact boxicity of the comparability graph of the Boolean lattice were posed as open questions in Discrete Mathematics, 349(7):115017, 2026. As a consequence of our results, we answer the latter question completely and the former question partially, by computing the exact boxicity of the power graphs of nilpotent groups.
AI 速览：TACache 提出免训练的“先跳步后补偿”缓存框架，通过沿整流流轨迹分解速度加速度来减少误差，从而加速扩散与整流流模型的采样。
Diffusion and rectified flow (RF) models generate high-fidelity images and videos, but their iterative velocity-field evaluations are computationally expensive. Existing caching methods accelerate sampling by skipping timesteps, yet their coarse approximations introduce accumulated errors over long skip intervals and degrade quality under aggressive acceleration. We propose TACache (Trajectory-Aware Cache), a training-free acceleration framework following a skip-then-compensate paradigm. TACache performs an orthogonal decomposition of discrete velocity acceleration along the RF trajectory into a parallel component and an orthogonal residual, isolating the magnitude and directional sources of per-step approximation error. The framework operates in two stages: offline, cumulative variation thresholds on the magnitude and direction indicators yield the skip schedule and bound how far each skip interval may extend; online, at each skipped step the offline statistics are combined with the sample's historical orthogonal direction to reconstruct the skipped velocity without additional model evaluations. Main comparisons on BAGEL, FLUX.1-dev, and Wan2.1-1.3B show that TACache achieves up to $4.11\times$ speedup on text-to-image generation and $2.11\times$ speedup on text-to-video generation, with consistent improvements over prior cache-based methods on most quality metrics. Our code is available at https://github.com/XiaoLiu1237/TACache.
AI 速览：该论文研究用最优传输松弛双射对齐来定义图距离时，最优传输版本与双射版本之间的整性间隙，并给出若干距离的上下界与计算复杂性结果。
A natural way to compare two graphs is to align their vertex sets by a bijection and to measure the difference of the aligned adjacency matrices in a matrix norm. Depending on the norm, this yields, for example, the edit distance, the cut distance, the spectral distance, and the local edit distance. To make these distances applicable to graphs of different order, one can consider blowups of the graphs or, equivalently, relax bijections to fractional alignments, that is, optimal transport plans between the uniform distributions on the vertex sets, in the spirit of Gromov-Wasserstein distances. We investigate how much the optimal transport versions can differ from their bijective counterparts, that is, we quantify their integrality gaps. For the edit distance, we improve the best known upper bound on the integrality gap from 3 to 2 and the lower bound from 6/5 to 4/3. For the cut distance, we approach Lovász's conjecture that $δ_\square \le 2δ_\square^{\rm OT}$ from both sides. We improve the previously best known upper bound $δ_\square \le 32 \cdot (δ_\square^{\rm OT})^{1/67}$ (Borgs, Chayes, Lovász, Sós and Vesztergombi, Adv. Math. 2008) to $δ_\square \le C_\varepsilon \cdot (δ_\square^{\rm OT})^{1-\varepsilon}$ for every $\varepsilon > 0$, and we construct graphs $G,H$ with $δ_\square(G,H) = 2δ_\square^{\rm OT}(G,H)$, establishing a factor-2 lower bound that matches Lovász's conjecture. For the local edit and spectral distances, we obtain upper bounds of order $\sqrt{t\ln(1/t)}$ and $\sqrt{t}$, respectively, where $t$ is the corresponding optimal transport distance, and we show that, unlike for the edit and cut distances, no linear upper bounds are possible. Finally, we show that computing the optimal transport distances is NP-hard, and we give hardness of approximation results for the cut, spectral, and local edit distances.
Timothy M. Chan, Reina Itakura, Zhiyuan Ma, Yuancheng Yu
AI 速览：作者给出检测或计数3-一致超图中4-超团的真正次四次算法，从而否证细粒度复杂性中一个流行假设。
We present truly subquartic algorithms for detecting or counting 4-hypercliques in a 3-uniform hypergraph with $n$ vertices, disproving a popular hypothesis in fine-grained complexity. The result immediately implies a faster algorithm for finding a $k$-hyperclique in a 3-uniform hypergraph for all constant $k\ge 4$, and a faster exponential-time algorithm for Max-3-SAT.
SAUCE: Summary Analysis Using Conversation Entailment
Man-Ling Sung, Hemanth Kandula, Jeff Ma, William Hartmann, Matthew Snover
AI 速览：提出一种无参考、基于事实的跨语言对话语音摘要评估流程，通过对话与摘要间的蕴含关系衡量摘要准确性与事实覆盖度。
With the growing need for evaluating Large Language Models (LLMs) and their applications to speech, challenges persist in summarizing and evaluating conversations that lack a clear end goal. We introduce SAUCE -- a reference-free, fact-based evaluation pipeline for cross-lingual conversational speech summarization. It measures the accuracy and the fact coverage of a summary through the entailment between conversation and text. We compare SAUCE against several popular summarization metrics and demonstrate the effectiveness of capturing information loss due to transcription and translation error and identifying broken summaries. Crucially, unlike black-box LLM evaluators or dense embedding metrics, SAUCE is inherently explainable: it maps summary scores to discrete, verifiable facts, allowing users to pinpoint exact hallucinations or omissions. We illustrate how this interpretability helps developers systematically profile LLM behaviors and gives end-users an actionable tool to verify summary accuracy in noisy, real-world conditions. Preliminary investigations show SAUCE strongly align with human judgment.
Evolutionary Design of Interpretable Spatial Descriptors for Structure-Property Relationship Discovery
Aditya Raghavan, Sergei V Kalinin
AI 速览：作者提出用遗传算法优化空间分区与池化操作，构建可解释的空间描述符，用于图像到局部谱和迟滞回线的回归预测。
Structure property prediction is a classical task in machine learning, ranging from molecular activity and materials properties to local functional responses measured in microscopy. For image-based regression, two choices define the information available to the predictor: the size of the image neighborhood and the spatial resolution retained within it. A small neighborhood can omit relevant surrounding structure, whereas a large, finely sampled neighborhood can introduce redundant or irrelevant information. Here, we develop a framework for constructing spatial descriptors for prediction of local spectra and hysteresis loops. We benchmark regression models, use SHAP maps to examine their spatial attribution, and explore the effect of the patch size and compression to establish the relationship between predictive accuracy and descriptor dimensionality. We then use a genetic algorithm to optimize spatial partitions and the assignment of mean, minimum, and maximum pooling operations. Each retained region contributes an explicit measurement of the image, allowing the search to balance prediction error against the number of descriptor values. Cartesian and polar constructions provide complementary ways to organize this information. The resulting descriptors make it possible to examine where spatial detail is needed, where regional summaries are sufficient, and how these choices depend on the predictor and the measured response. The same approach can be used for molecules and solids once the genetic algorithm rules for these are established.
LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting
Lingfei Qian, Yan Wang, Xueqing Peng, Yupeng Cao, Yuechen Jiang, Zhuohan Xie, Anke Xu, Wenbo Cao 等 15 位作者
AI 速览：作者提出 FinDendro 基准，检验大语言模型对自身时间性知识边界的自述是否可信，并发现自述普遍低估其实际知识。
Financial backtests of large language models (LLMs) are meaningful only if the model did not already know the outcomes it is asked to predict. Practitioners guard against this by trusting a vendor's stated knowledge cutoff, by asking the model what it knows, or by instructing it to answer as of a past date. To verify whether any of these safeguards can be trusted, we introduce FinDendro, a benchmark of 2,226 dated U.S. facts from 1999 to 2026, covering monthly macroeconomic series, month-end stock prices and Federal Reserve decisions. Each fact yields four prompts: a value question, Recall and Predict questions that pair each candidate value with a claim of knowing or guessing without a declared date, and a Predict question with a historical declared date. Controls for persistence and dominant outcomes keep chance accuracy near 0.27. Results show that for most frontier models, self-reports understate knowledge. GPT-5 answers 76% of controlled facts correctly but claims to know 38%, and answers 61% of the facts it says it does not know. Knowledge claims can persist beyond the measured knowledge boundary, by up to seven quarters, and a declared date removes most of the claims of prior knowledge while leaving accuracy unchanged. Backtests inside a model's training window therefore cannot be certified leak-free by self-report, instruction or stated cutoff. These findings motivate behavioral measurement of temporal knowledge boundaries, and FinDendro provides a benchmark and procedure for selecting backtest periods based on demonstrated factual knowledge.
Measuring Risk, Not Harm: Detecting Psychological Harm Risk Factors in LLM Conversations
Nil-Jana Akpinar, Eugenia Kim, Natalie Isak, Amanda Minnich, Victoria Westerhoff, Matthew Dressman
AI 速览：提出以“风险而非伤害”为思路，在AI回复层面检测八类可观察的心理伤害风险行为，并聚合信号用于纵向监测。
Psychological harms from interactions with large language models cannot be monitored directly because they may emerge over repeated interactions and depend strongly on subjective individual user context. We propose measuring risk, not harm: detecting observable AI behaviors that constitute risk factors for psychological harm at the AI response level and aggregating these signals to support longitudinal monitoring. We operationalize eight such behaviors and construct a synthetic multi-label corpus of 47,062 AI responses and 373,873 response-factor labels, with targeted human annotations for validation and evaluation. We then compare trained embedding-based classifiers, direct LLM judging, and a classifier--judge cascade. All detectors are model-agnostic and operate only on LLM outputs, requiring no access to internal model states. We apply these detectors to several out-of-distribution human-AI conversation data sets from prior research. On held-out human-labeled data, the best cascade achieves macro precision of 0.86, recall of 0.76, and F1 of 0.79. On WildChat, it reduces LLM-judge calls by 97.1\% relative to direct judging. On DelusionEval, risk-factor detections cluster within conversations. Together, our results show that response-level behavioral risk-factor detection can provide a scalable measurement layer for longitudinal psychological-safety monitoring without conflating observable AI behavior with latent user harm.
Monadically Dependent Graph Classes Have Almost Bounded Merge-Width
Jan Dreier, Nikolas Mählmann, Michał Pilipczuk, Szymon Toruńczyk
AI 速览：作者证明每个单子依赖图类都具有几乎有界合并宽度，并给出近立方时间的算法构造。
A graph class $\mathcal{C}$ is monadically dependent if one cannot interpret all graphs in vertex-colored graphs from $\mathcal{C}$ using a fixed formula of first-order logic. We prove that every monadically dependent graph class has almost bounded merge-width, thereby confirming a conjecture of the first and the last author [STOC '25]. Our proof is algorithmic and the witnessing decompositions in the form of merge sequences can be computed in nearly-cubic time. This is a step towards the proof of fixed-parameter tractability of model checking first-order logic on monadically dependent graph classes, which is achieved in a companion paper.
AI 速览：提出 CWMDT 框架，用数字孪生结构化表示场景并借助大语言模型推理干预传播，从而把标准视频扩散模型改造为可回答反事实查询的世界模型。
World models learn to predict the temporal evolution of visual observations given a control signal, potentially enabling agents to reason about environments through forward simulation. Because of the focus on forward simulation, current world models generate predictions based on factual observations. For many emerging applications, such as comprehensive evaluations of physical AI behavior under varying conditions, the ability of world models to answer counterfactual queries -- such as "what would happen if this object was removed?" -- is of increasing importance. We formalize counterfactual world models that additionally take interventions as explicit inputs, predicting temporal sequences under hypothetical modifications to observed scene properties. Traditional world models operate directly on entangled pixel-space representations where object properties and relationships cannot be selectively modified. This modeling choice prevents targeted interventions on specific scene properties. We introduce CWMDT, a framework to overcome those limitations, turning standard video diffusion models into effective counterfactual world models. First, CWMDT constructs digital twins of observed scenes to explicitly encode objects and their relationships, represented as structured text. Second, CWMDT applies large language models to reason over these representations and predict how a counterfactual intervention propagates through time to alter the observed scene. Third, CWMDT conditions a video diffusion model with the modified representation to generate counterfactual visual sequences. Evaluations on two benchmarks show that the CWMDT approach achieves state-of-the-art performance, suggesting that alternative representations of videos, such as the digital twins considered here, offer powerful control signals for video forward simulation-based world models.
Task-Efficient Agent Evaluation Using Cached Traces
Ben Johnson, Hayden Helm
AI 速览：作者提出用 LLM 提取轨迹结构化摘要并嵌入，构建参考系统的低维几何表示，从而用少量任务执行估计智能体在完整基准上的表现。
Efficient benchmarking estimates a system's full benchmark performance from a small number of task executions. Standard approaches rely solely on the binary correctness of executions from a collection of already-evaluated reference systems. An agentic system, however, produces a rich trace for each execution that can reveal substantially more about its capabilities. Leveraging this information requires useful trace representations. We propose representing a trace by extracting a structured summary of it with an LLM and embedding the summary with a standard text encoder. These representations preserve correctness- and task-related signal while minimizing the presence of system identity-, model family- and harness-related signals that dominate raw trace embeddings. Given this representation for each task execution from all reference systems, we construct low-dimensional representations of the systems and predict a new system's score from its position among the reference systems. On SWE-bench Verified and Terminal-Bench 2.0, augmenting an item-response model with this geometry-based prediction reduces mean absolute error from 0.13 to 0.08 (Wilcoxon $p < 10^{-4}$) and from 0.14 to 0.12 (Wilcoxon $p < 10^{-3}$), respectively, when provided a single random executed task. Further, given access to the full set of reference systems, our approach dominates baselines for any given number of executed tasks on both benchmarks.
ConDR: Conservative Reachability through Neural Hamilton-Jacobi Subsolutions
Kendra Givens, Taylor T. Johnson, Bryan C. Ward, Thomas Beckers
AI 速览：提出保守版 DeepReach（ConDR），通过单边损失学习 HJI 变分不等式的次解，使学到的不可达安全集包含真实不安全集，从而减少不安全状态被误判为安全的情况。
Hamilton-Jacobi (HJ) Reachability identifies the unsafe states of a dynamical system from which it can be forced into failure under worst-case disturbance. However, classical grid-based solvers scale exponentially with state dimension. DeepReach improves scalability by replacing the grid with a neural value function trained on the HJ-Isaacs (HJI) variational inequality (VI), but penalizes both sides of the residual equally. This allows the learned value to lie above the true one and unsafe states to be misclassified as safe. We propose Conservative DeepReach (ConDR) which aims to learn a subsolution of the HJI VI such that the learned unsafe set contains the true one. ConDR enforces the obstacle branch and terminal condition by construction, pushes the HJI residual to a safety margin $ε$ below zero with a one-sided loss, and prevents the degenerate solution of classifying everything as unsafe. We prove that the exact solution of the margin-shifted VI that ConDR trains toward is a subsolution of the original VI so its unsafe set contains the true one and its value lies within $ετ$ of the true value function. We compare against DeepReach and MADR in the established systems of Air3D, Air6D, a 9D multi-vehicle system, and a 13D quadrotor. ConDR reports the lowest rate of unsafe state misclassified and the lowest closed-loop collision rates with at most a small increase in intervention. On Air3D and Air6D, ConDR tolerates model mismatch that scales with $ε$. At matched false-negative rates, ConDR's unsafe sets are smaller than the baselines showing the safety is not obtained by trivial over-approximation.
Jorge Luiz Franco, Arthur Queiroz Moura, Moacir Ponti, Amauri Souza
AI 速览：作者提出将消息传递融入图过滤过程的拓扑描述子 MGP，并报告其在表达力和多个图任务上优于既有基于持续同调的描述子。
Message-passing graph neural networks (GNNs) are limited in expressive power by the one-dimensional Weisfeiler-Leman test. Persistent homology (PH) provides topological descriptors that can complement GNN representations, but existing approaches typically compute persistence separately from the representation learning process. In this paper, we introduce Message-Passing Graph Persistence (MGP), a family of topological descriptors that incorporates message passing into graph filtrations. At each filtration step, node embeddings are updated using the current subgraph and associated with persistence events. These embeddings also determine the representatives of connected components during persistence computation. We prove that MGP is invariant under graph isomorphism and that it is strictly more expressive than the PH-based descriptors it extends. We evaluate MGP on an expressivity benchmark and on several graph classification and regression datasets. Experiments show that MGP outperforms other PH-based descriptors on most of these datasets.