Research

• Real-time request execution in streaming video generation1 paper raises it · 0 address it

  Models struggle to reliably follow incremental user requests while maintaining state consistency in interactive video generation.

  • StreamEval: Evaluating Interactive Streaming Video Generation Modelsraises
• Brain-body mismatch in recursive self-improving agents1 paper raises it · 1 addresses it

  Evolving execution scaffolds (harnesses) can outpace or restrict the capabilities of the underlying model, leading to misalignment.

  • CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow?raises · addresses
• End-to-end deep search in open web environments1 paper raises it · 1 addresses it

  Agents fail to autonomously explore, integrate, and verify evidence from diverse, interactive, and heterogeneous web sources.

  • Deep Search in Real-World Web Environmentsraises · addresses
• Length generalization in state tracking1 paper raises it · 1 addresses it

  Models trained on short sequences often fail to generalize to much longer sequences without explicit progress alignment.

  • PAR: Progress-Aligned Recurrence for Length Generalization in State Trackingraises · addresses
• Fine-grained geometry and appearance recovery in 3D Gaussian Splatting1 paper raises it · 1 addresses it

  Feed-forward models struggle to capture detailed structures and textures in 3D scene reconstruction.

  • FineSplat: Fine Patches, Local Groups, Detailed Splatsraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.AIOct 13

  Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

  Yuan Liu, Haoyue Peng, Fanliang Hu, Lei Huang, Wenli Cai

  Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning quality. We present an adaptive multi-agent controller (ADMA) that learns continuous policies for proposal, challenge, arbitration, and coordination while keeping the task model frozen. Shared trace features describe quality, agreement, and progress, while role-specific features support decentralized control during inference. One controller trained on legal and financial reasoning is transferred without policy updates to four textual and multimodal benchmarks and two successive task-model versions. With Qwen3.5 held fixed, ADMA-Full improves accuracy by 6.2-14.2 percentage points over Direct and by 2.8-3.0 points over ADMA-Fixed. Paired bootstrap ranges for the Full-Fixed comparison are positive on three tasks. Outcome decompositions show that recoveries exceed introduced errors, while process assessment records fewer false-consensus events and more supported correct outcomes. Transfer to Qwen3.6 remains task dependent, which bounds the generality of the learned policy. Median token and latency ratios are…

  PDF

  Summarize this
• arXiv cs.CROct 13

  ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?

  Fasheng Miao, Zhaoyu Hu, Xiang Li, Changqing An, Jiutian Zeng +3

  Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation that depends on interactions among network protocol components. Such vulnerabilities arise from inconsistencies in message interpretation, timing, state, or trust assumptions across participants. We introduce ProtoArena, a black-box, multi-component, dynamic benchmark with 80 cross-component vulnerability-exploitation environments spanning 11 protocol and application domains and 7 attack categories. Tasks are primarily informed by published protocol-attack mechanisms. Agents interact with running systems through scoped interfaces to achieve security-effect objectives without target source code. Three information levels assess guided reproduction, exploitation with mechanism and topology context, and effect-directed black-box exploration. A hybrid verifier combines rule-based checks with LLM review of independently collected traffic and logs. We evaluate five LLMs. Claude Opus 4.8 achieves the highest observed success rates: 48.8% under L1 guidance and 12.5% under effect-directed black-box L3. In a separate DNSBomb optimization…

  PDF

  Summarize this
• arXiv quant-phOct 13

  A Tutorial on Quantum Amplitude Embedding with Data Re-Uploading

  Hyojun Ahn, Joongheon Kim

  Amplitude embedding lets a variational quantum model read many classical features with few qubits, but the model output is then only a quadratic form in the normalized input. Data re-uploading, which encodes the input repeatedly between trainable blocks, can be used to enrich such a model. Because every additional upload of an amplitude embedding repeats a costly state preparation, the gain that an upload buys has to be known before the gates are spent. This tutorial thus addresses the problem of explaining what data re-uploading adds to an amplitude-embedded model and how large the gain is. We express sequential re-uploading and parallel re-uploading with two copies in one notation and show that each upload raises the reachable polynomial order by two. Under one trainable circuit family and one budget of trainable parameters, simulation results show that re-uploading raises the test coefficient of determination from 0.689 to between 0.883 and 0.975 on targets of order four and from 0.337 to between 0.642 and 0.783 on targets of order six, on all ten seeds. On a quadratic target and on handwritten digits, one upload remains the best choice, and every additional upload lowers the…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design

  Yu Zeng, Yuchuan Chen, Ziyue Zhang, Zijian Wei, Yanyi Su +3

  Materials and chemical optimization must choose the next synthesis, characterization, or high-fidelity simulation from sequential observations under a limited budget. Large language models can use task knowledge to propose adjustments, but composing surrogates, acquisition functions, and search strategies is constrained by compatibility, parameter dependencies, and evidence requirements. We present Agentic-MatriBO, a capability-compiled agentic Bayesian optimization (BO) framework that represents BO components and selection conditions as composable capabilities. A language policy proposes BO recipes and candidate plans; a compiler checks proposals against the registered capability catalog; and a deterministic execution layer validates and commits candidates. Oracle observations are stored in research memory and inform later rounds. We compare Agentic-MatriBO with eight baselines on four offline finite candidate pools---COF, PCE10, Buchwald--Hartwig (BH), and Suzuki--Miyaura---using five seeds per condition; results are reported descriptively. Across the four tasks, Agentic-MatriBO has the best mean endpoint quality after orienting each objective so that higher is better. On COF,…

  PDF

  Summarize this
• arXiv cs.SEOct 13▲ 8

  Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing

  Xiaolong Xu, Hao Jiang, Bo Jiang, Zhiwen Deng, Ningyuan Sun +3

  Diffusion large language models (dLLMs) are appealing for code generation because they can update many tokens in parallel, yet many are optimized for sequence synthesis rather than edit prediction. This setting is poorly matched to modern AI-assisted IDEs, where edit prediction must infer the next code change from recent edits, the current file, and cursor-local context. Such changes are usually sparse and preserve most source tokens, so regenerating a full code segment wastes computation. We propose Diff Diffusion, a diffusion-inspired LLM framework for code editing that predicts edit paths from an original snippet to its revised form. Diff Diffusion represents denoising as structured edit operations, and combines this formulation with multi-stage training and efficient parallel decoding. By focusing computation on changed regions, Diff Diffusion supports accurate low-latency edits and multi-position parallel modification. Across public edit-completion benchmarks, edit-prediction evaluations, and online validation, Diff Diffusion matches or leads autoregressive baselines while delivering 2.78 times faster inference on public edit-completion benchmarks and a 39.0% P50…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

  Tiancheng Shen, Zilong Huang, Xiangtai Li, Zhijie Lin, Jiyang Liu +4

  Multimodal Diffusion Transformers (MM-DiTs) have recently emerged as a powerful framework for unified text-vision synthesis, surpassing traditional U-Net architectures in generative tasks. One key innovation lies in its Multimodal Self-Attention (MM-SA) interaction, where image and text tokens are concatenated and processed via self-attention. However, this mechanism poses significant challenges for editing, rendering conventional U-Net-based attention manipulation methods ineffective. To address this limitation, we propose QK-Edit, a training-free framework that exploits the unique attention dynamics of MM-DiTs for precise text-guided image and video editing. By introducing a novel query-key manipulation strategy, our method isolates and adjusts critical attention components to achieve an optimal balance between prompt fidelity and structural consistency. This enables seamless edits across various tasks, including object addition, object removal, object replacement, changing background, changing material, changing color, and style transformation. Notably, it can be easily implemented with feature replacement in inference. QK-Edit demonstrates superior editing performance on…

  PDF

  Summarize this
• arXiv cs.AIOct 13

  Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents

  Haochen Zhao, Minsheng Hao, Zheng Li, Yifan Li, Zikang Liu +6

  Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back to retrieved evidence. Recent methods track citations to enforce grounding, but citation support alone does not establish source independence or whether an answer appropriately handles conflicting evidence. We argue that credibility in open-web retrieval depends on principled cross-source evidence grounding that accounts for source independence and systematically attributes and adjudicates conflicting evidence, while hierarchical judgments of these grounding decisions provide a unified signal for training and evaluation. To this end, we propose an evaluation framework, Cross-Source Evidence Grounding (CSEG), that employs a fine-grained, six-layer decision tree over the complete search trajectory. We introduce CSEG-Bench and trainable reward models to provide targeted supervision following this framework. Our approach helps eliminating the severe data skew of natural trajectories by providing targeted coverage over complex, deep-layer decision paths, such as cross-source conflict resolution and nuanced attribution, that standard…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR

  Savyasachi Gupta, Aniruddha Srinivas Joshi

  Reinforcement learning with verifiable rewards (RLVR) has become a principal recipe for improving the reasoning of large language models (LLMs). It rests on the assumption that the checker scoring each response is itself correct. In practice, rule-based checkers reject correct answers in unexpected formats, unit tests accept incorrect programs, and LLM judges can be led to approve empty or adversarial responses. This work surveys 58 studies that measure, analyze, or mitigate such verifier errors. We ask what errors verifiers make, how they affect training, which mitigations work against which errors, and how the findings extend to self-generated, rubric- and judge-based, and verifier-free rewards. The evidence suggests that the structure of an error matters more than its rate. Random errors mostly slow learning, though under a fixed budget or KL regularization they also lower final accuracy. False positives that the policy can learn to trigger can cause plateaus or collapse, sometimes even with a low initial error rate. Whether a verifier wrongly rejects or accepts depends on what it checks and who built it, not on its family. Its errors shift as the policy improves, and most…

  PDF

  Summarize this
• arXiv cs.CROct 13

  Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers

  Xiang Li, Aichun Huang, Mingming Zhang, Zheli Liu

  TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer defines in advance and returns a probability for each answer. The vendor admits that adversarial input can change these answers but gives no numbers. In this paper, we present the first controlled adversarial evaluation of Jev. We build a test harness that sends every system the same payload under the same policy, and run it on four public-data tasks, from rule-based ones (input moderation, injection detection, routing) to a judgment-based one (phishing detection), with fifty attack variants from thirteen families. The targets are Jev, five GPT and GLM judges, and two local classifiers (Llama Guard 3, Prompt Guard 2). We find that Jev is the most robust system on input moderation: eight forgeries of its structured input bypass none of its decisions, and a sentence asking only why someone might make a harmful request bypasses 9% of its blocks, against 56% for GPT-6 Astra. On phishing detection. However, the same forgeries bypass 19-29% of the emails it flags, and even without attack Jev detects only 62% of phishing emails, against 77-81% for the GLM judges. Jev is…

  PDF

  Summarize this
• arXiv cs.LGOct 13

  Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Convex Sets

  Chen-Yu Wei

  We give the first adversarial linear bandit algorithm based on Follow-the-Perturbed-Leader (FTPL) that achieves $\sqrt{T}$ regret over general convex action sets. Our algorithm attains $\widetilde{\mathcal{O}}(d^{5/4}\sqrt{T})$ regret using only linear optimization oracles, and the near-optimal $\widetilde{\mathcal{O}}(d\sqrt{T})$ regret when an optimal-design exploration distribution is further available. This improves on the $T^{2/3}$ regret of the FTPL algorithm of Dani and Hayes (2006) for general convex sets, and generalizes the $\sqrt{T}$ regret of Lévy et al. (2026) over two special action sets (hypercube and Euclidean ball). Compared to previous oracle-efficient linear bandit algorithms based on continuous exponential weights, the FTPL approach generally has better computational efficiency, and is much simpler to implement. The key algorithmic element is a perturbation distribution that adapts to the past reward estimators. Its simplest form, an adaptive Gaussian perturbation, is straightforward to implement and already attains the regret bound above. We further extend it to two general constructions, random-weighting and elliptical perturbations, each covering…

  PDF

  Summarize this
• arXiv cs.AIOct 13▲ 14

  Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution

  Pengcheng Huang, Zhenghao Liu, Shixin Ren, Shi Yu, Sijia Yao +3

  Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-hosted models. However, as LLM agents increasingly operate in long-horizon scenarios, cloud participation becomes interleaved throughout execution rather than a one-shot decision for each query. Such interleaved participation introduces trajectory-level effects that remain insufficiently understood. To address this gap, we introduce EC2-Bench, a benchmark for evaluating edge-cloud collaboration in long-horizon agent execution. It provides executable digital-workspace agent tasks and a unified evaluation framework covering task performance, resource usage, and privacy exposure. Using this benchmark, we empirically study diverse forms of edge-cloud collaboration. Our study reveals three findings. First, collaboration achieves a favorable balance among task performance, resource usage, and privacy exposure compared with edge-only and cloud-only execution. Second, as edge models become stronger, collaborative execution approaches cloud-only performance, and performance differences across strategies shrink, while privacy exposure…

  Code
• arXiv cs.CLOct 13

  Perturbation, Not Provenance: Why Activation Steering Does Not Make a Robust Text Watermark

  Sergey Pletenev

  Linear directions in the activation space of large language models causally and universally influence model behavior. This suggests that they might serve as a basis for a robust text watermark. The idea is to steer the generation along a specific semantic direction and then recover the mark by probing the activations of the re-encoded text. We test this hypothesis by conducting a series of experiments. We vary the strength of the steering and use four different directions (formality, sentiment, complexity, and a random control) across two different model families. We also test two paraphrasing attacks: a sentence-level one and a stronger paragraph-level one. The results show that activation-steering watermarks are outperformed by a standard logit-based watermark (KGW) in terms of detection accuracy. At a matched level of fluency (within 1.15 times the original text's perplexity), KGW achieved an AUC of 0.81 against a sentence-level paraphraser, while the best steering direction only reached 0.65. A stronger paragraph-level paraphraser lowered both (0.65 for KGW and 0.59 for steering), narrowing the gap but not reversing it. On Qwen, it left the two indistinguishable but at…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis

  Juho Jung, Seongjae Kang, Mijoo Kim, Sungduk Cho, Yunkyoung Jun +2

  Pixel-level annotation for chest X-ray (CXR) lesion segmentation is expensive, making active learning (AL) essential. However, existing AL strategies fail to account for the spatial distribution of selected samples, resulting in inconsistent performance across focal (e.g., aortic calcification) and diffuse (e.g., nodules) pathologies. In this paper, we propose SPARCL (Spatially Adaptive Regional Coverage for Active Learning) to dynamically balance predictive uncertainty with cumulative spatial coverage. By employing a concave coverage function, SPARCL imposes diminishing returns on previously annotated regions, naturally directing the annotation budget toward under-labeled areas. Furthermore, an entropy gate reverts the algorithm to standard uncertainty sampling when spatial variation is absent. This coverage objective is monotone submodular, guaranteeing near-optimal greedy batch selection. To address how aggregate metrics like Dice obscure regional failures, we further introduce two metrics---Spatial Inconsistency (SI) and Performance Coverage (PC)---to quantify anatomical fairness across AL rounds. Evaluated on an in-house calcification cohort and public CXR benchmarks, SPARCL…

  PDF

  Summarize this
• arXiv cs.CLOct 13

  BRIDGE: Selective Boundary Repair with Dependency Graph Evidence in Multi-Agent Systems

  Encheng Su, Pengze Li, Ziheng Hua, Qiucheng Yu, Jianyu Wu +10

  Multi-agent collaboration has emerged as a critical paradigm for tackling complex, long-horizon tasks; however, while coordination protocols continue to advance, systemic failures at the inter-agent collaboration interface remain a pervasive bottleneck. In collaborative workflows, systems frequently suffer from \emph{broken handoffs}---where critical task context is omitted, misrouted, or ignored despite each agent emitting locally plausible responses. To address this challenge, we present \method, a verifiable runtime control framework that treats handoff repair as selective intervention over explicit dependency graphs. Central to \method is an integrated fault-attribution and calibration pipeline, \dataset, which decouples execution dependencies and injects counterfactual handoff perturbations to provide empirical supervision for runtime intervention. Leveraging this diagnostic foundation, \method dynamically compiles observable interaction traces into a provenance graph to pinpoint unresolved dependencies, without accessing private agent states. It then evaluates candidate repairs through an empirical gate that weighs expected gains against disruption risks, and executes…

  PDF

  Summarize this
• arXiv cond-mat.mtrl-sciOct 13

  Learning from fracture: Teaching language models to design through physical experience

  Bo Ni

  How can language models learn to optimize physical designs through experience? We introduce FracLearn, an experience-abstraction-generalization framework evaluated through a deliberately unfamiliar, Tetris-inspired fracture game. The model first proposes architectures and examines simulated fracture responses to accumulate experience. Abstraction organizes these observations into conditional principles linking reinforcement placement, crack evolution and load transfer, with supporting evidence and failure conditions. Generalization challenges the model to combine these principles in new architectures and surpass the earlier design record. Campaigns demonstrate progressive refinement and recovery through hypothesis revision, yielding a best composite score 11.0% above the experience-stage record. Fracture analyses connect improved performance to crack deflection and temporary trapping as toughening mechanisms, alongside greater residual load capacity. Learning occurs through external knowledge and decisions, without model-weight updates. This approach offers a route to scientific agents that turn computational experiments into reusable physical knowledge for materials discovery…

  PDF

  Summarize this
• arXiv cs.ROOct 13

  Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations

  Bo-Ruei Huang, Daniel Seita, Erdem Bıyık

  Robot manipulation has traditionally relied on end-effector-centric interactions. In contrast, humans routinely exploit whole-arm contacts to improve efficiency, robustness, and adaptability, especially when the hands are occupied or when precise grasping is unnecessary. Enabling similar capabilities in robots remains challenging: the robot must select where on its arm to make contact, generate effective non-prehensile interactions, and satisfy task-specific pose or safety constraints on the end-effector. We propose Whole-Arm Contact Learning (WACL), a hierarchical framework that describes each whole-arm contact task with three robot-agnostic representations and hands them to a quasi-static surface-contact optimizer: semantic keypoints that summarize the scene, a reference contact trajectory that specifies where and how the arm presses on the object, and safety-aware path constraints that a vision-language model generates from the task description to protect the end-effector's task. The robot's kinematic chain enters only in this optimizer, which grounds these representations onto the arm by jointly searching over which link makes contact, where on that link, and the joint…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  Multimodal Fusion of RGB and Complementary Modalities for Semantic Segmentation

  Hu Cao, Yifeng Cheng, Mu He, Mengyu Li, Yinlong Liu +1

  Multi-modal semantic segmentation adds an auxiliary sensing stream to RGB images (RGB-X), such as thermal, LiDAR, depth, event, polarization, or light field. This can improve robustness in poor lighting and under motion blur. But different sensors often produce features that do not match well, and fusion can become unstable. To alleviate these issues, we propose a bidirectional polarity-aware cross-modality fusion (BPCF) module that effectively captures complementary cues while enhancing feature alignment. We evaluate the framework on six modality pairings: RGB-Thermal, RGB-LiDAR, RGB-Depth, RGB-Event, RGB-Polarization, and RGB-Light Field. Our model achieve state-of-the-art (SOTA) results on eight public datasets, including MFNet, KITTI-360, DELIVER, DDD17, DSEC, MCubeS, ZJU, and UrbanLF. The codes and trained models will be released upon acceptance.

  PDF

  Summarize this
• arXiv cs.LGOct 13

  GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation

  Xu Liu, Hanshu Yan, Taha Aksu, Quang Pham, Zhongzheng Qiao +4

  Contextual forecasting seeks to improve time series forecasting by incorporating forward-looking information, such as planned events, external conditions, and expert expectations. However, reliable evaluation remains difficult: existing benchmarks often have limited domain coverage, lack standardized history-future splits, or provide text that is not guaranteed to inform the future. We introduce GIFT-Eval-CTX, a benchmark that isolates whether forecasting methods can translate verified future information into accurate numerical trajectories. Built upon GIFT-Eval, GIFT-Eval-CTX contains 10,000 instances across 20 datasets. Each instance provides structured effects derived from the realized future: Macro effects describe horizon-wide behavior, while Micro effects specify localized changes. We construct these annotations with an agentic pipeline combining LLM-based discovery and deterministic code validation. We benchmark TSFMs, frontier LLMs, and tool-using agentic systems. The results show that structured effects reduce aggregate relative MASE by 40.7% for GPT-5.6 Sol and 29.6% for Claude Opus 4.8 relative to history-only prompting. The evaluated MoiraiAgent system achieves the…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search

  Minghua Chen, Xingming Liao, Weiqiang Zhong, Zhuowei Wang

  GUI grounding enables web agents to translate natural-language instructions into actionable interface locations. However, dense layouts and small, visually similar controls can lead models toward plausible but incorrect elements, while refinement around a single prediction may leave alternative targets unexplored. We propose the Multi-Hypothesis Verification Framework (MHVF) for training-free GUI grounding. It combines multi-hypothesis exploration with local visual verification using a single pretrained vision-language model. To explore alternative targets, MHVF constructs spatial hypotheses from multiple full-screen predictions and examines the corresponding regions through zoomed re-localization. To resolve ambiguity among the resulting candidates, it verifies their agreement with the instruction in marked local views. Verification scores then guide a second round of local search and rank candidates retained from both search levels for final selection. Experiments with five general-purpose and GUI-specific models across eight benchmark settings demonstrate improvements in grounding accuracy in most settings. MHVF improves UI-Venus-Ground-7B by 4.3 and 2.1 percentage points on…

  PDF

  Summarize this
• arXiv cs.CVOct 13

  When, Where, and Why: Hierarchical Causal Explainability for Video Face Understanding with MLLMs

  Anubhav Kataria, Shreya Ghosh, Jingwen Ye, Abhinav Dhall

  Understanding facial behaviour in video requires answering three fundamental questions: when a key facial expression occurs, where the model attends on the face at that moment, and why that evidence is necessary rather than merely correlated. Today's multimodal large language models (MLLMs) can label and describe video, but they rarely provide faithful explanations, especially for small facial movements that change over time. We present VideoFace-X-LLM, a framework for explainable facial video understanding comprising two key components. First, we introduce ExplainFace, a weakly supervised video-text corpus for facial behaviour understanding, automatically constructed from CelebV-HQ videos and validated through human evaluation and a two-model audit (at most 2.3% contradictions), demonstrating consistent gains across two backbone architectures. Second, H-TCC (Hierarchical Temporal Spatial Causal Concepts), which finds the key temporal moments (When), the facial regions (Where), and verifies its causal necessity (Why) through targeted occlusion. Fine-tuning on ExplainFace raises appearance Macro F1 from 19.48% to 32.87% (+13.39), with gains of +4.38 on actions, +6.77 on temporal…

  PDF

  Summarize this

• Adversarial training42−14.3%
• Anomaly detectors29−14.7%
• Forecasting time62−20.5%
• Federated learning36−23.4%
• CAD models12−25.0%
• Teacher policy distillation46−28.1%
• Image segmentation145−28.9%
• Frontier LLMs365−29.1%