Weight-space programming for auditing clinical decision networks
Humza Nusrat, Omar Nusrat
AI 速览：作者报告前沿语言模型仅凭临床协议和网络权重即可盲审并修复小型放疗决策网络中的部分植入缺陷，但尚不能证明网络正确。
Machine learning models in radiotherapy are commissioned by testing them on cases with known answers, which may not reveal a shortcut that the test cases share with the training data. Frontier language models have recently been reported to read and write the raw weights of small neural networks, an ability called weight-space programming. The purpose of this study was to determine whether such a model, given only a clinical protocol and a network's weights, can audit and repair the network. Networks with 433 to 4,801 parameters were trained to screen head-and-neck planning requests against four rules. Flaws were planted through the training data: confounds that hid each rule, a 3 Gy shift in the cord threshold, and a hidden trigger. Claude Opus 5.5 audited each network blind, without tools, data or code execution, and every claim and repair was tested on about 420,000 requests. The language model named the broken rule in 16 of 18 flawed networks (95% CI 67% to 97%), including all 15 with a confound or a threshold shift. It repaired each of the 16 by changing a median of 3 parameters. Fine-tuning on protocol-labeled requests also repaired every network, but changed nearly every parameter. Each confound and shift it found was visible in single units, and a simple statistic chosen for each flaw type found the same flaws. It cleared 2 of 5 healthy networks without being forced and found 1 of 3 triggers. Testing against the protocol detected every flaw, and black-box testing found the confounds and the shift faster. The results indicate that, in small networks, weight-space programming can locate and repair flaws that silence an input or shift a threshold, but cannot yet certify that a network is correct.
MedPhysBench: A Benchmark for Evaluating Language Models on Medical Physics Calculations and Error Detection
Omar Nusrat
AI 速览：作者构建了一个覆盖放疗、诊断影像、核医学与辐射防护的医学物理计算与查错基准，并报告了12个语言模型在留出测试集上的表现。
Medical physicists turn a prescription into a delivered dose and check one another's calculations, because one error in a beam calibration or a monitor-unit (MU) calculation can affect every patient treated with it. MedPhysBench has ten seeded generators of calculation items in radiation therapy, diagnostic imaging, nuclear medicine and radiation protection, up to clinical tasks such as a TG-51 calibration worksheet. Reference answers come from code implementing the governing protocols, and a grader converts units and applies tolerance bands. From the same inputs, separate checking items test error detection, showing a colleague's worksheet or only the colleague's result, half correct and half with one planted error. On a held-out test split of 1,200 items (half for two models), 12 models scored 33.3 to 100.0% on calculation. Of the nine answers graded incorrect for the four best (99.3-100.0%), five contained model errors and four followed NCRP Report 151 on points our items misstate or leave open. Below them, most models did worst on level-3 clinical tasks, and Claude Sonnet 5.5 omitted the inverse-square correction in 19 of 20 isocentric MU items. Five models detected at least 96.7% of mostly large planted errors with at most 4% false alarms; for four of the other seven, checking only the result raised false alarms significantly. In an exploratory targeted test with 20 public cases of an omitted inverse-square correction, the three best models tested caught it in every worksheet, and three weaker models accepted 16 to 18 of 20 planted worksheets, one of them while applying the correction in most of its own calculations. Claude Opus 5.5 accepted 6 of 20 wrong results, although it applied the correction in all 20 of its own. We report the effect of two problems in our shielding items, found after the runs, and release the code, per-item outcomes and targeted-test responses.
Enterprise teams that deploy large language model (LLM) agents inherit a maintenance problem that traditional testing does not address. The model is non-deterministic, but the larger risk is that most of what changes an agent's behavior (a retired model version, a revised policy, an upstream schema change, a prompt edit meant to fix one case) originates outside the owning team and is discovered as a production defect rather than caught as a regression. This paper presents Agentic Behavior Engineering (ABE), a platform-agnostic methodology that treats observable agent behavior, rather than the prompt or the model, as the version-controlled engineering artifact. ABE adapts Design by Contract to non-deterministic systems. A specification-only behavior contract with stable rule identifiers states what the agent must do, must not do, and when it must abstain for lack of evidence; a lightweight scenario library turns each rule into concrete situations; and every engineering artifact (tests, runtime policies, telemetry) references the contract in one direction only, so that specification and implementation can change independently without drifting apart. The method organizes the work into five responsibilities (Specify, Ground, Control, Verify, Observe), treats missing evidence and a verified negative as different things, enforces authority outside the model, gates releases on per-scenario pass^k reliability rather than aggregate accuracy, and classifies every production run against the contract so that each finding routes to the asset that must change. We illustrate the method with an executable capacity-allocation boundary suite and a constructed worked example of a product-review approval workflow.
AI 速览：提出分位数传播规划（QPP），用少量固定扰动分位数经动力学传播并积分代价曲线，在有限模型评估预算下同时评估均值与尾部风险。
Risk-aware planning must identify rare, costly outcomes using only a limited number of model evaluations. Monte Carlo rollouts spend this budget on noisy tail estimates, while planning from the mean can miss the tail entirely. We introduce quantile propagation planning (QPP), which propagates a small, fixed set of disturbance quantiles through the dynamics and integrates the resulting cost curve to evaluate both mean and tail risk. The method is exact at the propagated levels, converges as the quantile grid is refined, and admits a one-sided conservatism guarantee under stated structural conditions. In controlled overload and inventory tasks, QPP reduces realized tail cost and constraint violations relative to mean-rollout planning. On overload, it remains competitive with sampled evaluators that use substantially more trajectories. These results position QPP as a transparent, budget-controlled approach to tail-risk evaluation.
Benjamin Pikus, Daniel Saunders, Mircea Mironenco, Salman Mohammadi, Mathew Mathew, Sirou Zhu, Divya Makkar, Xuhua Huang 等 14 位作者
AI 速览：提出ZAP方法，在仿真中仅用简单任务和模型自身成功经验训练小型开源VLM，使其获得运动控制技能，从而在真实机器人任务上达到与GPT-6 Astra相当的成功率，且更快更便宜。
Frontier models such as GPT-6 Astra now directly control robots and can generalize better than vision-language-action models (VLAs). We argue that this ability could arise from two distinct, composable skills: semantic reasoning, to understand what a task asks for in a scene, and motion control, to move the robot to do it. We show that small open VLMs are already capable of the first and mainly lack the second. We introduce Zero-real Agent Policy (ZAP), a recipe that teaches this missing motion skill, entirely in simulation on simple primitive tasks and from the model's own successes, with no frontier teacher or distillation and no real-world robot data. ZAP reaches 96.7% success on real-world tasks, matching GPT-6 Astra in our harness while running 3x faster and 17x cheaper, and 74.0% on a bimanual adaptation of RoboLab-120, on par with GPT-6 Astra's 72.2%. ZAP also generalizes to new objects, goals, and strategies, and in simulation to a robot embodiment on which it never trained.
Plotkin-optimal pure quantum LRCs with large minimum distances from NMDS codes
Yang Li, Shitao Li, Gaojun Luo, San Ling
AI 速览：该文提出从Hermitian对偶包含的NMDS码构造达到Plotkin类界的纯量子局部可恢复码（qLRC）的一般框架，并基于ESGRS码给出四族构造。
Quantum locally recoverable codes (qLRCs) are a class of quantum error-correcting codes that can recover an erased qudit by accessing only a few other qudits. This paper develops a general framework for constructing optimal pure qLRCs that attain the Plotkin-like bound, referred to as Plotkin-optimal pure qLRCs, from Hermitian dual-containing near maximum-distance separable (NMDS) codes. Focusing on a special class of NMDS codes called extended subcodes of generalized Reed-Solomon (ESGRS) codes, we determine their localities by analyzing certain subset sum problems over finite fields. By further exploiting the algebraic structures of ESGRS codes and related codes, we construct four families of Plotkin-optimal pure qLRCs with large lengths and more flexible minimum distances than existing constructions. These constructions provide strong global error-correction capability while retaining local recovery. To the best of our knowledge, they give the first families of qLRCs attaining the pure Plotkin-like bound. In addition, by using the resulting locality property, we resolve in the negative a related problem on ESGRS codes supporting combinatorial designs.
A simple adaptive accelerated optimistic dual averaging method for unconstrained convex optimization in $p$-norm geometry
Bowen Li, Danqing Zhou, Chuan He
AI 速览：作者提出 A²ODA，一种在 p∈[2,∞] 的 p 范数几何下采用低成本预条件、无需线搜索的自适应加速乐观对偶平均方法，并给出收敛界。
Efficient preconditioning plays an important role in large-scale first-order optimization. In this paper, we propose an adaptive accelerated optimistic dual averaging ($\text{A}^2$ODA) method for unconstrained convex optimization that adopts low-cost preconditioning based on $p$-norm geometry for $p\in[2,\infty]$. The method is line-search-free and employs a new stepsize selection technique based on an aggregated affine lower model. Its update structure is simple and unified across $p\in[2,\infty]$, with the case $p>2$ requiring no more elaborate updates than the Euclidean case $p=2$. Under a generalized local smoothness condition, we derive a convergence bound that separates the effects of constant and gap-dependent curvature, with the latter potentially yielding faster-decaying terms. In the special case of local smoothness, this bound recovers a nearly optimal convergence rate.
Gayatri Deshmukh, Onkar Susladkar, Adheesh Juvekar, Halil Kilicoglu, Ismini Lourentzou
While discrete tokenization in Unified Multimodal Models (UMMs) establishes strong semantic reasoning, it introduces a strict quantization bottleneck that degrades fine-grained visual details, often resulting in structurally accurate but artifact-heavy images. We introduce FlowShift, a parameter-efficient post-training framework that bypasses this bottleneck by converting pre-trained discrete UMMs into continuous rectified-flow generators. Instead of discarding the backbone's semantic priors, FlowShift replaces discrete visual interfaces with continuous latent projections and applies LoRA to the attention layers. To efficiently boost visual quality without semantic drift, we propose Dual-Objective Velocity Vector Distillation (DOVD), which aligns the model with a high-fidelity continuous teacher and ground-truth continuous trajectories. This approach drastically improves perceptual quality while preserving prompt adherence and reasoning. When applied to leading discrete UMMs, FlowShift significantly improves COCO-30K FID and aesthetic scores, while retaining over 99.5% of multimodal understanding capabilities. Ablations confirm DOVD drives generation quality. Ultimately, FlowShift achieves high-fidelity continuous generation without sacrificing pre-trained semantic grounding.
LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
Rodney Lafuente-Mercado, Salman Rahman, Jingyan Shen, James Shiffer, Saadia Gabriel, Pavel Izmailov
AI 速览：LeanPRM 利用 Lean 证明助手自动为自然语言证明生成步骤级标签，训练无需人工标注的步骤验证器。
AI systems now write long and difficult mathematical proofs, and checking their step-by-step validity is becoming a bottleneck. A learned verifier could check proofs cheaply, but training one requires a correctness label on every step, and such labels are hard to obtain for open-ended proofs. Existing methods take them from human annotators, which is costly, or derive them from final answers, which proofs do not have, and formalizing each proof in Lean requires expert effort. We introduce LeanPRM, a framework that uses the Lean proof assistant to create step-level labels for natural-language proofs. A model writes a natural-language proof together with a paired formal proof, without feedback from Lean. Lean then labels every step, and a second model discards failures caused only by the formal syntax, so that the negative labels mark errors in the mathematics. LeanPRM contains 10,634 proofs with 152K labeled steps and no human annotation. A Qwen3-4B verifier trained on LeanPRM raises exact step-label accuracy on a held-out set of 200 proofs (LeanPRM-Bench) from 48.2 to 74.7, as opposed to 60.3 when the same base model is trained on PRM800K. It also selects better proofs in best-of-N selection on IMO-level problems, and outperforms the PRM800K-trained verifier on three of four external verification benchmarks. Training on LeanPRM improves verifiers at every size from 0.6B to 8B parameters on LeanPRM-Bench, Hard2Verify and IMO-GradingBench. Given the labels need no human annotation, LeanPRM can grow with the supply of formal statements, offering a path to step-level feedback on AI-generated proofs that are hard for humans to check.
CATF: A Manager-Worker Framework for Context-Aware Time-Series Forecasting
Yueqiao Chen, Dongyu Liu
AI 速览：提出一种基于 Manager-Worker 架构的上下文感知时间序列预测框架，用 Transformer 经理按上下文硬路由到单个专家工人，使任意单模型预测器无需人工划分数据即可实现专业化。
We study context-aware time-series forecasting, in which a single target variable is predicted from its own history and a set of contextual variables, such as weather and calendar information. As the context becomes more diverse, a single model struggles to capture all of its regimes, while ensemble learning and Mixture-of-Experts approaches rely on manual data partitioning or soft routing, which increases the inference cost and hinders interpretability. We propose CATF, a Context-Aware Time-Series Forecasting framework built on a Manager-Worker architecture: a Transformer-based Manager routes each input to a single Worker based on the context, using hard routing during both training and inference. The Workers thus specialize without manual data partitioning, and any single-model forecaster can serve as a Worker. On five context-rich datasets, four horizons, and two normalization schemes, CATF improves over its standalone counterpart in 162 of 200 comparisons, the best CATF-enhanced model outperforms the best standalone baseline in 19 of 20 settings, and it outperforms the zero-shot Time-MoE foundation model in 15 of 20 settings. A case study on bike-sharing data shows that the Manager routes inputs by the calendar and that each Worker specializes in a different weekly pattern.
Scaling Graph Reasoning in Language Models with Learnable Graph Positional Encodings
Javier Porras-Valenzuela, Arush Arora, Alejandro Ribeiro
AI 速览：作者提出用可学习的、置换等变的图位置编码调制语言模型注意力，并以GNN加Graph Transformer计算编码，从而避免序列化邻接表、把上下文负担降到O(N)。
Solving reasoning tasks supported on graphs typically requires providing a Language Reasoning Model (LRM) with a serialized description of the graph. This approach results in the input length growing with the number of edges, which limits the size of the problems that can be solved. Furthermore, even when graphs fit in context, performance sharply decays as the graphs grow. We propose to address this by augmenting LRMs with scalable and permutation equivariant graph positional encodings that modulate attention logits. An additional post-fusion-style module incorporates structural information into hidden states. We compute these positional encodings using a GNN followed by a Graph Transformer. This eliminates the need for serialized adjacencies, reducing the context burden to $O(N)$. We jointly fine-tune the positional encoder and the LRM LoRA adapters using optimal solutions generated by graph-theoretic solvers, resulting in a computationally efficient method. Trained on small graphs, the model exhibits improved size-generalization across graph-theoretic tasks on graphs with up to 1,000 nodes, and produces fewer tokens than a conventional LRM. Additionally, we observe that our model remains robust to node relabelings.
AI 速览：作者提出让编码智能体在仿真中重建任务并生成带动作标签的逼真多视角数据，以替代人工遥操作采集机器人示范。
Teleoperation remains the default way to collect robot demonstrations, but every episode costs robot and operator time, and every new task starts from scratch. We ask whether a coding agent can take over the teleoperator's job. In our DataFarm, the agent receives a data request and one calibration episode of the robot in the target scene and rebuilds the task in simulation: it writes the scene, an expert controller, and a success judge. The simulator supplies exact actions, and a video model conditioned on real images renders each rollout as photographic video, generating all camera views together consistently. The output is real-ready data: synchronized camera views labelled with the robot's actions, on which a policy can be trained directly and deployed on the real robot. Independent judges certify the expert and every rendered episode before admission. On five real-robot tasks, policies trained only on farm data match policies trained on as many teleoperated episodes (93 vs. 84 successes in 100 trials), and under an unseen tablecloth and coloured light they keep 87 successes where the teleoperation-trained policies fall to 46. Adapting a task is fully automatic and costs \$21 of API usage on average, paid once per task, plus \$5 for a render contract; every further episode costs \$0.80 on average for simulation, rendering, and review, with no robot or operator. One hour of three-view data for a task costs \$107 on average, these costs included, slightly below a quote of \$117 for teleoperation in China and below \$290 in labour alone in North America.
HARP: Training-Free Dual-Profile Agentic Communication for LLM-Based Recommendation
Zhen Tao, Xun Zhou, Xuhui Chen, Ziyue Qiao, Qingqiang Sun
AI 速览：将LLM推荐重构为四阶段智能体通信过程，并用免训练的三算子方法HARP补齐物品画像、检索端画像同质性与画像反思更新三个缺失环节。
In LLM-based recommendation, memory acts as a user-level agent in a memory-augmented backbone. Yet users and items remain asymmetric: only the user is given a structured profile; it enters a bandwidth-limited reranker prompt; and it is frozen after warmup. We recast LLM-based recommendation as an agentic-communication process in four stages: BUILD a self-description, TRANSMIT it along the collaborative graph, UNDERSTAND the other side, and SYNC it from the next interaction. This formulation reveals three unresolved communication challenges: the item side never produces a comparable self-description (one-sided BUILD); profile-level signals enter only the bandwidth-limited reranker prompt rather than retrieval, where they would not compete for context tokens (prompt-trapped UNDERSTAND); and the user's description is frozen after warmup with no principled update rule (absent SYNC). We instantiate the missing stages as HARP (Homophily-aware Agentic Recommendation via dual Profiles), a training-free, three-operator addition to a frozen LLM backbone: a rule-extracted symmetric item profile (zero extra LLM calls), a channel-decomposable profile-level homophily H(phi_u, phi_i) consumed at retrieval time rather than inside the reranker prompt, and a single-pass reflective update realising in-context profile evolution without any gradient step. On four public benchmarks (Yelp, Books, MovieTV, Goodreads), HARP lifts Hit@1 over the strongest published baseline by 6.9%-24.0%, with family-wise Holm-corrected p < 1e-9 on every dataset. Ablations and a per-case attribution study show that the operators contribute complementary gains, with the retrieval-side gate as the main source; we also report the trade-off introduced by the reflective pass. We formulate agentic communication and provide a training-free instantiation. Code is available at https://github.com/Jove-Zhen/HARP.
Large Growth Happens: Gaussian Elimination with Partial Pivoting on Random Matrices
Daniel A. Spielman, Xifan Yu
AI 速览：作者证明对高斯随机矩阵做带部分主元的高斯消元时，出现大幅增长的概率至少是逆拟多项式级别，从而挑战了平滑分析与平均情形分析中的标准猜想。
We prove that the probability that Gaussian elimination with partial pivoting on $n \times n$ Gaussian random matrices has growth $ρ$ is at least inverse quasi-polynomial: $Ω\left(\exp\left(-c \log^2 \left(\fracρ{\sqrt{n}}\right)\log(n)\right)\right)$ for some constant $c > 0$. In particular, the probability of growth $ρ\ge n^{1/2 + ε}$ is at least $\exp(- O (ε^2 \log^3 (n) ))$. This lower bound breaks standard conjectures in the smoothed and average-case analysis of Gaussian elimination. To the best of our knowledge, it is the first non-trivial lower bound on the probability of large growth for Gaussian random matrices.
Noisy Issues, Noisy Results: Mislabeling in Information Retrieval-based Bug Localization
Moumita Asad, Rafed Muhammad Yasir, Yirui He, Ziyao He, Sam Malek
AI 速览：大规模实证研究发现IRBL基准数据集中平均34.82%的问题报告存在错误标注，剔除这些噪声会显著降低六种IRBL技术的评测性能，但不改变技术间的相对排名。
Information Retrieval-based Bug Localization (IRBL) leverages bug reports to identify faulty source files. Evaluations of IRBL approaches primarily rely on labeled issues from issue tracking systems. However, prior research has shown that issue labels are frequently incorrect in open-source projects, threatening the validity of IRBL evaluations. Existing studies have primarily examined traditional IRBL techniques on small datasets, overlooking modern approaches and the partial overlap between noisy and cleaned datasets. In this paper, we conduct a large-scale empirical study to investigate the prevalence and impact of mislabeled issues in IRBL benchmarks. We analyze five benchmark datasets comprising over 55,000 issue reports and find that, on average, 34.82% of issues are mislabeled. We further evaluate six IRBL techniques, spanning traditional, deep learning-based, and large language model-based approaches using the widely adopted Ye et al. benchmark and statistical methods that account for dataset overlap. Our results show that removing mislabeled issues from evaluation datasets significantly reduces measured performance across all six techniques, with Mean Reciprocal Rank decreasing by 4.68%-21.74%. Although mislabeling does not change the relative ranking of techniques, it affects the magnitude of their performance differences. These findings highlight the importance of reliable evaluation data for ensuring valid and meaningful comparisons of IRBL techniques.
AI 速览：MDSKILL 将技能记忆按状态定位、动作规划与执行控制三个功能视角组织，并用动态指标筛选高质量技能，再通过在线策略自蒸馏把互补经验内化到共享策略中，以提升智能体自我进化效率。
Skill memories encode past experiences as textual prompts to improve reinforcement learning (RL) for self-evolving agents. Complementing RL, On-Policy Self-Distillation (OPSD) provides dense, fine-grained supervision to internalize knowledge from skill-guided trajectories and accelerate policy learning. However, self-generated memories often contain noisy supervision and functionally entangled, redundant, or conflicting knowledge, making direct distillation difficult. Under limited training budgets, these issues can hinder knowledge internalization and even degrade performance. To address this problem, we propose MDSKILL, a multi-view distillation approach for skill memory internalization. MDSKILL organizes skill memories into three complementary functional views (state grounding, action planning, and execution control) and selects high-quality skills using dynamic metrics to construct view-specific and integrated reasoning branches. OPSD then transfers and consolidates complementary experiential knowledge across these branches into a shared policy, enabling efficient skill internalization and continuous agent self-evolution. We evaluate MDSKILL on three agent benchmarks against RL, skill-augmented, and self-distillation baselines that do not rely on stronger external teacher models. Without additional computational overhead, MDSKILL improves upon SOTA performance by up to 7.1% and 8.1% on ALFWorld and WebShop. Extensive ablations and evolution analyses further validate its effectiveness in knowledge internalization and policy improvement. The code is available at https://anonymous.4open.science/r/MDSKILL-CF53.
Roundtrip All-Pairs Shortest Paths in Directed Graphs
Shiri Chechik, Gur Lifshitz
AI 速览：研究有向图在往返度量下的全对最短路径近似算法与距离预言机，给出新的算法上界与基于 BMM 的下界。
We study approximation algorithms for All-Pairs Shortest Paths (APSP) in directed graphs under the roundtrip metric. In directed graphs, even finite-factor approximation of ordinary one-way distances must distinguish reachable from unreachable vertex pairs, and therefore computes transitive closure, a problem equivalent to Boolean matrix multiplication (BMM) under standard reductions. The roundtrip distance, defined as $\text{dist}_G(u \leftrightarrows v) = \text{dist}_G(u \to v) + \text{dist}_G(v \to u)$, offers a natural and robust relaxation. It measures the cost of traveling from $u$ to $v$ and back, satisfies the triangle inequality, and is inherently symmetric. While this metric has become central to the study of directed roundtrip spanners and compact routing, the fundamental problem of all-pairs roundtrip distance approximation has remained largely unexplored. In this work, we present a comprehensive study of roundtrip APSP and distance oracles, presenting several new lower and upper bounds. On the algorithmic side, our main result is a combinatorial algorithm that computes a stretch-$3$ approximation to all-pairs roundtrip distances in $\widetilde{O}(n^2 + \min\{m\sqrt{n},\, m^{1/3}n^{5/3}\})$ time. For edge weights in $[1,W]$, we also obtain a $(3+\varepsilon)$-approximation in $\widetilde O((n^{2.037}+nm^{2/3})\log(nW)/\varepsilon)$ time and a $(4+\varepsilon)$-approximation in $\widetilde O(n^{2.032}\log(nW)/\varepsilon)$ time using fast matrix multiplication. On the hardness side, we show that any stretch below $3$ would imply a breakthrough for BMM. We also obtain additional tradeoffs between stretch and running time.
$Φ$asmaNet: A Staged Spectral Token-Refinement Architecture for Fast Gravitational-Wave Signal-to-Noise Ratio Prediction
Ioannis Tsioulis, Anastasios Tefas, Nikolaos Stergioulas
AI 速览：作者提出紧凑神经网络 ΦasmaNet，以分阶段谱精炼为显式架构先验，快速预测进动高阶模式双黑洞信号的相位平均最优信噪比。
Quantifying selection effects in gravitational-wave population studies requires millions of costly signal-to-noise ratio (SNR) calculations. We present $Φ$asmaNet, a compact neural architecture for structured tabular regression, with staged spectral refinement as an explicit architectural prior. Learned input tokens are refined through ordered attention-based $Φ$-Stages, each augmented by a $Φ$-Refractor subspace-mixing module, then revisited through gated top-down $Φ$-Feedback. Applied to the 11-dimensional parameters of precessing, higher-mode binary black hole signals (IMRPhenomXPHM), it predicts phase-averaged optimal SNR for a single detector at fixed Advanced LIGO design sensitivity. With approximately 732k parameters, it outperforms MLP, 1D-ResNet and Transformer-encoder baselines under matched training across $10^5$--$10^6$ samples. At $10^6$ samples, it achieves $100-\mathrm{MAPE}=98.73\%$ on the held-out test set, $99.29\%$ after rank-preserving monotonic (PCHIP) calibration, and $99.39\%$ ($R^2=0.9998$) in the detection-relevant regime $ρ>8$, with stable accuracy across independent dataset realizations. On a single GPU, it sustains approximately $1.2\times10^5$ SNR evaluations per second and processes a $10^6$-injection catalogue end-to-end in approximately 8.3 s, about two orders of magnitude faster than conventional waveform-and-inner-product calculations on a 16-core CPU. Exact distance rescaling through $ρ\propto1/d_L$ supports repeated catalogue-wide detectability evaluations. The fully documented pipeline is intended as a reproducible benchmark, while results on public tabular datasets indicate competitiveness beyond gravitational-wave applications. Although demonstrated for a fixed single-detector configuration, the construction supports extensions to detector networks and epoch-specific sensitivities. (Abridged)
AI 速览：提出首个无需训练、以文本引导编辑眼科手术视频的框架，通过二阶ODE反演与注意力Value张量注入，在保持眼部解剖结构的同时实现器械替换与手术阶段变化。
High-fidelity surgical video generation holds great promise for medical training and AI development, yet precise, controllable editing of such videos remains a formidable challenge. Modifying surgical attributes such as instrument, tissue interactions or procedural phases is particularly difficult due to the strict anatomical and temporal constraints of ophthalmic procedures. We introduce OphEdit, the first training-free framework for text-guided editing of ophthalmic surgical videos. Our approach uses a deterministic second-order ODE inversion pipeline to capture attention Value tensors from the source video and selectively injects them into the conditional branch of classifier-free guidance during denoising, preserving the intricate anatomical geometry of the eye while mapping text-driven semantic modifications onto the video. Clinical evaluation by an ophthalmologist shows that OphEdit handles complex transformations, such as instrument swaps and procedural variations, with superior structural fidelity and temporal consistency compared to adapted general-domain video editors, offering a scalable route to diverse surgical training data. The code and prompts can be accessed at https://github.com/ophedit/OphEdit
Noah Fleming, Mika Göös, Ziyi Guan, Oliver Korten, Daniel Mitropolsky, Toniann Pitassi, Artur Riazanov, Dmitry Sokolov 等 10 位作者
AI 速览：作者在随机预言机模型（Romantica）中刻画了主要 TFNP 类的平均情形困难性，并给出 PPAD 困难、EoPL 与 UEoPL 可解性分离等结果。
We determine which major $\TFNP$ classes are hard in the random oracle model (ROM). Prior work establishes average-case hardness of highly structured subclasses of $\TFNP$ from strong cryptographic assumptions such as LWE and indistinguishability obfuscation. It is not known whether weaker assumptions such as one-way functions imply hardness of any of the standard $\TFNP$ subclasses, even in the worst case. The ROM, where all parties have query access to a random function, lies, morally, between these two regimes: a random function is one-way, but public-key cryptography cannot be built from it in a black-box way. We refer to this setting as \emph{Romantica}. Our first result settles a long-standing open problem: $\PPAD$, the class of total search problems reducible to finding a Nash equilibrium, is hard on average in Romantica. Combined with the known hardness of PLS (local search), this gives average-case hardness of $\EoPL = \PPAD \cap \PLS$. In contrast, we show that $\UEoPL$ can be solved in Romantica with polynomially many oracle queries by a computationally unbounded solver, a sharp distinction between $\EoPL$ and $\UEoPL$. This resolves the black-box hardness landscape of all major $\TFNP$ classes in Romantica. Finally, we initiate the study of separations between $\TFNP$ subclasses in Romantica: $\PWPP$ and $\PPA$ do not reduce to $\PLS$ under \emph{public-coin} reductions.
Peter Belcak, Saurav Muralidharan, Jindong Jiang, Yonggan Fu, Wonmin Byeon, Hanrong Ye, Ryan Angilly, Ali Taghibakhshi 等 12 位作者
AI 速览：作者报告通过频繁压缩上下文，前沿语言模型在长程与长输入任务上几乎不损失准确率，并据此质疑长上下文模型的必要性。
Later tokens are costlier to generate than earlier tokens. On frontier open weight models, the disparity in cost may rise to as much as 7x. Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accuracy when maintaining short contexts. We further demonstrate that LLM performance does not collapse on long-horizon software engineering tasks even when taking at most one action per context, and based on that we outline the concept of semantic state space models (SSSMs). Our findings question the need for long-context language models.
Looped transformers are a parameter-efficient alternative to standard transformers for language modeling. By reapplying the same layers across multiple loop steps, recent looped language models match the performance of non-looped models several times their size. While this architecture effectively reduces parameter memory, each loop step still stores its own keys and values, so the key-value (KV) cache grows linearly with the number of loop steps and becomes the main memory bottleneck. We observe that the KV cache of looped models is highly redundant along the loop axis and that the loop steps differ substantially in their sensitivity to quantization. Based on these observations, we propose $\textbf{LoopVQ}$, a KV cache vector quantization method for looped transformers that codes channels of multiple loop steps jointly, and fine-tunes the codebooks to match the output of the full-precision model. At 0.5 bits per element, LoopVQ outperforms existing KV cache vector quantization methods for standard LLMs on general, long chain-of-thought reasoning, and long-context retrieval tasks with Ouro and Huginn models. Its design is orthogonal to these methods, and combined with TaSQ, it retains much of the BF16 accuracy even at 0.25 bits per element. We also implement LoopVQ in SGLang, where it nearly halves the decode latency at a 32K-token context and raises the peak serving throughput by up to $4.3\times$ and $6.1\times$ on the 1.4B and 2.6B Ouro models compared to the BF16 baseline.
AI 速览：作者通过构造经典与酉 oracle，表明量子性证明和量子验证者 oblivious 态制备可与 P=NP、BQP=QCMA 等计算易性共存，因而量子优势对复杂性理论的含义有限。
We consider the complexity implications of proofs of quantumness and (quantum verifier) oblivious state preparation. We show that both of these objects can coexist with the easiness of nondeterministic computation. That is, we give evidence that proofs of quantumness can exist when $\mathsf{P} = \mathsf{NP}$ and that (quantum verifier) oblivious state preparation can exist when $\mathsf{BQP} = \mathsf{QCMA}$. In particular, we give a classical oracle relative to which (1) $\mathsf{P}^\mathcal{O} = \mathsf{NP}^\mathcal{O}$ (2) $\mathsf{BQP}^\mathcal{O} = \mathsf{PSPACE}^\mathcal{O}$ (3) Proofs of quantumness exist. In particular, there exists a language in $\mathsf{IP}^\mathcal{O} \subseteq \mathsf{BQP}^\mathcal{O}$ which is hard on average against $\mathsf{P}^\mathcal{O}/poly$. We give a unitary oracle such that (1) $\mathsf{BQP}^\mathcal{O} = \mathsf{QCMA}^\mathcal{O}$ (2) Quantum verifier oblivious state preparation exists. These oracle separations directly imply a number of related consequences. For example, our first result implies that proofs of quantumness cannot be used to construct classical or quantum cryptography with a relativizing proof. Our second result implies that quantum computation/classical communication oblivious transfer cannot be used to construct post-quantum one-way functions with a relativizing proof.
PACT: Pose-Robust Actuation Co-Design for Tendon-Driven Robotic Hands
Prashant Kumar, Rachael Granberry, Taylor Niehues, Andrew A. Stanley, Gabe Pirie
AI 速览：提出PACT框架，在姿态相关力需求与驱动带宽约束下联合优化腱走线、力臂与绞盘尺寸，用于腱驱动机械手设计。
Humanoid robotic hands must provide sufficient force, speed, and backdrivability within a human-scale envelope. Tendon-driven transmissions address this challenge by relocating actuators to the palm and forearm, but routing paths, moment arms, and capstan dimensions jointly determine both force capability and joint speed, so selecting them sequentially satisfies one requirement at the expense of the other. This paper presents a pose-robust actuation co-design for tendon-driven robot hands (PACT) framework that optimizes tendon routing, moment arms, and capstan dimensions under pose-dependent force requirements and drivetrain-bandwidth constraints. A feasible-force formulation enforces actuator bounds and equilibrium at all joints, while a max-min objective maximizes task-force coverage at the weakest pose. Applied to a four-degree-of-freedom finger, the framework produces an asymmetric N + 1 tendon topology using quasi-direct-drive actuators. Across eight poses, the design achieves task-force coverage of 0.88-1.00 and a predicted 5 Hz minimum isolated-joint flexion/extension bandwidth within a 70th-percentile human-size envelope. Prototype measurements deviate from predictions by up to 24.5%, primarily due to unmodeled transmission losses. These results indicate that co-designing routing with the drivetrain can meet pose-dependent force requirements without relaxing the bandwidth constraint, paving the way for human-sized robotic hands with human-level performance.
Counterexamples to the Happy Edge Conjecture in Plane Spanning Trees
Oswin Aichholzer, Joseph Dorfer, Peter Kramer, Christian Rieck, Birgit Vogtenhuber
AI 速览：作者通过构造16点一般位置与30点凸位置的反例，否定了关于平面直线生成树重配置中快乐边在最短翻转序列中不被翻转的民间猜想。
We study the problem of reconfiguring plane, straight-line spanning trees on point sets in the plane. A flip is a reconfiguration step in which one edge of a tree is replaced with another, yielding again a plane spanning tree. For a given point set $P$, the flip graph has a vertex for each plane spanning tree on $P$, and an edge between any two trees that differ by a single flip. The folklore happy edge conjecture suggests that any edge shared by both the initial and the target tree (a happy edge) is never flipped in a shortest flip sequence. This conjecture was computationally verified for up to 10 points in convex position. In this paper, we disprove this conjecture both on general point sets and on point sets in convex position by providing two counterexamples on $16$ and $30$ points, respectively. The counterexample for point sets in general position also holds for compatible flips, while the happy edge property holds for compatible flips in convex point sets as shown by Aichholzer, Dorfer, and Vogtenhuber [GD 2025].
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Burc Gokden
AI 速览：PLDR-LLM 的幂律图注意力（PLGA）在理论上精确包含缩放点积注意力（SDPA），但作者报告其头评分算子在推理时趋于输入不变，导致推理坍缩为每头使用常数算子的广义 SDPA。
The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bilinear form of scaled dot-product attention (SDPA) with a learned, input-generated bilinear operator $G_{\mathrm{LM}}$, built from a positive tensor $A_{\mathrm{LM}}$ by elementwise power laws. The architecture is fully specified, verified against pinned reference releases; claims are labeled theorem, conditional theorem, measurement, or conjecture. Unconditionally: PLGA contains SDPA exactly at $G_{\mathrm{LM}}=I$; $A_{\mathrm{LM}}$ and $A_{P}$ are strictly entrywise positive, with Perron-Frobenius structure on $A_{\mathrm{LM}}$; the DAG regularizer has the NOTEARS walk-counting form and positivity obstructs exact acyclicity; and, under nonresonance (satisfied by standard rotary frequencies), a commutant criterion identifies which operators preserve relative-position dependence. An inference-collapse theorem: exact input invariance of the head score operators $G_{\mathrm{LM}}$ collapses inference to generalized SDPA with a constant operator per head. Measured invariance: relative fluctuations of $10^{-6}$ and below; perturbation bounds quantify but do not certify cached inference; the assembled proxy misses the decoding margin. A conditional three-stage mechanism (rotary twirl, concentration, row-map contraction) is measured on a released checkpoint. Blockwise training and scoring under the global Gram are stated with explicit target exposure; on tested samples, block and sequential scoring select identical answers and agree on the published TruthfulQA probability-mass metric within $5\times10^{-5}$ per item. Self-organized criticality enters as a phenomenological framework with an intrinsic order parameter; open claims become falsifiable conjectures. Selected proof cores are machine-checked in Lean 4.
AI 速览：作者提出统一测试框架 uni-robot-agent，使开放权重模型可开展机器人使用智能体研究并支持后续训练，报告开箱即用的 Qwen3.8-Flash-Next 在 RoboDojo 上取得 31.39 分。
Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary models limits research into further training. To democratize RUA research, we introduce uni-robot-agent, a unified harness for competitive open-weight robot use that supports further training. Without privileged inputs, an out-of-the-box Qwen3.8-Flash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.
AI 速览：作者通过凸对偶将硬核引理推广为基于掩蔽信道保真度的通用硬度认证框架，覆盖非布尔函数与多种损失。
We prove a broad learning-theoretic generalization of the celebrated hardcore lemma concerning the average-case complexity of computing a Boolean function (Impagliazzo, 1995). Our starting point is the observation that the classic notion of a hardcore measure, which reweights a function's input distribution, is equivalent to an input-dependent masking channel that injects randomness into the function's output distribution until it appears fully pseudorandom. The analogue of density of the measure is the fidelity of the channel. From this viewpoint, we develop a general framework for certifying hardness that allows for non-Boolean functions $f$ and a wide range of notions of hardness besides the classic 0-1 loss, by choosing the right notion of fidelity via convex duality. We show the difficulty of learning $f$ using a class $\mathcal{C}$ to minimize a convex loss is tightly characterized by the maximum fidelity possible for a masking channel, which measures the least amount of noise the channel must add to hide the structure of $f$ and make it $\mathcal{C}$-indistinguishable from random noise. Using our framework, we derive a number of multiclass generalizations of the hardcore lemma, and reveal some unexpected subtleties in going to larger alphabets. We construct a universal masking channel that applies to many natural notions of hardness simultaneously. Such channels are dual to omnipredictors, which optimize multiple losses at once (Gopalan, Kalai, Reingold, Sharan, and Wieder, 2022). We observe a symmetry between masking channels and generalizations of the hardcore lemma using pseudoentropy. We present a tight characterization of pseudoentropy using the MaxEnt algorithm from machine learning. A long line of research has shown that learning and hardness are two sides of the same coin; our framework gives a crisp and general formulation of this principle via convex duality.
GSBR: Geometric Support Behavior Regularization for Online RL
Charles Xu, Jacob Berg, Liyiming Ke, Sergey Levine
AI 速览：提出 GSBR，用动作到基策略支撑集的距离做正则化，在支撑集内不惩罚、支撑集外平滑惩罚，以兼顾在线 RL 的探索改进与稳定性。
Regularizing online reinforcement learning (RL) toward a pretrained base policy can improve sample efficiency and learning stability, but regularization that is too restrictive limits how much the policy can improve. Base policies -- typically diffusion or flow-matching models trained by imitation learning on large, diverse datasets -- capture many behaviors that are reasonable but suboptimal. Existing regularizers using such base policies are too restrictive in one of two ways: behavioral cloning regularizers pull the actor toward the full base-policy distribution, penalizing it for discarding suboptimal modes, while hard support constraints forbid improvements that lie just outside the base policy's support. We propose Geometric Support Behavior Regularization (GSBR), which penalizes actions by their distance from the base policy's support. Actions within the support incur no penalty, so the actor can concentrate on high-value modes; outside the support, where value estimates are less reliable, the penalty grows smoothly with distance while still permitting improvement when the value gained outweighs the penalty. GSBR estimates this distance from a finite set of base-policy samples, so it requires only sample access to the base policy. Across 19 tasks on four robotic benchmarks, GSBR raises the average success rate from 33% for the base policy to 95%, achieving the highest average success rate and throughput among all compared methods, with about 23% higher normalized throughput than the next-best RL method. Project website and open-source code at https://charlesxu0124.github.io/gsbr/ .
Wonder 4: A Mixture-of-Experts Recipe for Image Quality Enhancement
Yunan Wu, Bin Sun, Partha Acharjee, Xiaoyu Wang
AI 速览：作者提出 Wonder 4，一种混合专家（MoE）模型，可同时修复真实照片中多种退化，并让每种修复作用于其发生区域。
A real photograph is often blurry, grainy, compressed, scratched, and low-resolution at the same time. Each defect has its own severity and its own place in the image. The corrections for these defects conflict with each other. Exist- ing models describe the whole image with one description, so they cannot say where each correction belongs. To solve this problem, we present Wonder 4, a mixture-of-experts (MoE) model for image quality enhancement. It corrects several defects of a real photograph at the same time, each in the region where it occurs. Every block of the model holds a mixture of N = 13 experts. A router, trained with the model, sends every image patch to k = 5 of them. No degradation classifier, mask, prompt, detector, or task label is used. Another issue is that standard MoE training, taken from language models, pushes every expert toward equal use. Equal use applies every correction everywhere, even where it is not needed. We replace this rule with a bias that only sets a minimum share of use. Across all patches, an expert used less than this minimum gets higher router scores until it is selected again. An expert above the minimum is not changed, so no expert is forced to be used as often as the others. The bias needs no extra loss. The method adds no extra module and no extra processing step. We evaluate Wonder 4 on DIV2K and Flickr2K, against five published methods and three open-weight pipelines. It reaches the best LPIPS, DISTS, and NIQE on all three test settings (DIV2K x4, DIV2K x8, and Flickr2K x4).