# Research Papers — 2026-08 · bundle page 143 of 240 > Full-text markdown of papers #7101–7150 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/143 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/142.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/144.md) ### A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench Authors: Praveen Reddy, Charuta Mandke, Suvrankar Datta, Sarah Khan, Siddharth Reddy Anthireddy, Shitij Arora, Vishal Singh Published: 2026-08-12 Categories: cs.CL, cs.AI, cs.HC, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2608.12138v1 General-purpose large language models (LLMs) have recently been reported to match or exceed specialized clinical AI tools on medical benchmarks, but such comparisons draw on a narrow set of systems and on benchmarks developed largely in high-income settings. We evaluate VITA, a retrieval-augmented generation (RAG) system purpose-built for contextual knowledge retrieval in India and other low- and middle-income (LMIC) settings. VITA retrieves from a curated corpus of disease-specific guidelines, India-specific antimicrobial resistance data, national formulary constraints, and resource-limited care protocols; its architecture and corpus are proprietary, but the benchmark, the physician-written rubrics, and our full response and scoring outputs are public for independent verification. On 4,023 English-language HealthBench questions (80.5% of the benchmark), scored with a GPT-4.1 judge, VITA ranked first with 51.9% of possible rubric points, ahead of GPT-5.4 (46.1%), o4-mini (44.3%), Gemini 3.1 Pro (42.6%), and Claude Sonnet 4.6 (37.3%), and scored highest on 45.4% of questions. To test robustness to newer models and judge lineage, a 500-question subset was re-run against current-generation models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Pro, Grok 4.3) and graded by a neutral open-weight judge (DeepSeek-V4-Pro) sharing no lineage with any system tested. Here the gap narrowed to parity: VITA and GPT-5.5 were statistically indistinguishable on mean per-question score, while VITA led on points-weighted score and won the most questions. VITA's advantages in accuracy and completeness persisted under the neutral judge; its communication scores were lower. These results indicate that a purpose-built clinical RAG system remains competitive with frontier LLMs on an open benchmark, consistent with corpus specificity as a design variable that improves grounding at some cost to communication polish. --- ### Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids, and Full-Bandit Learning Authors: Vaneet Aggarwal Published: 2026-08-12 Categories: cs.LG, cs.AI, cs.CC, math.OC arXiv: https://arxiv.org/abs/2608.12134v2 We study nonnegative submodular maximization on $n$ elements subject to a general matroid of rank $k$, when the offline algorithm is given an arbitrary controlled value oracle. Our main result is an adversarial resilience theorem for the Spiteful Greedy Swap Poisson Process (SGS-Poisson): without modifying its Poisson intensity, single-element exchange rule, or spiteful drop step, the algorithm retains limiting approximation factors $1/e$ for non-monotone objectives and $1-1/e$ for monotone objectives. More precisely, given an error bound $ξ\ge0$, under every controlled oracle $\widehat f$ satisfying $|\widehat f(S)-f(S)|\le ξ$ for every set $S$, our implementation returns a feasible set with expected value at least $(1/e-\varepsilon)OPT-O(kξ)$ and $(1-1/e-\varepsilon)OPT-O(kξ)$, respectively, where $OPT$ is the feasible optimum. The implementation uses a \emph{deterministically bounded} budget of $O(nk^{2}\varepsilon^{-2}\log n\log^{2}(1/\varepsilon))$ oracle calls. As a consequence, an offline-to-online reduction yields full-bandit combinatorial multi-armed bandit (CMAB) algorithms for general matroid-constrained submodular rewards with exact limiting approximation-regret factors $1/e$ and $1-1/e$ and $\widetilde O(n^{1/5}k^{4/5}T^{4/5})$ regret over $T$ rounds. These online guarantees allow exploration to play sets that become independent after deleting at most one element; exploitation and the benchmark remain matroid-feasible. For unit-capacity partition matroids we obtain $\widetilde O(n^{1/5}k^{3/5}T^{4/5})$ under the same exploration relaxation. We establish a deterministic query budget by truncating the Poisson process and identify the enlarged action set needed to answer its offline queries. --- ### Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids: From Robust Offline Optimization to Full-Bandit Learning Authors: Vaneet Aggarwal Published: 2026-08-12 Categories: cs.LG, cs.AI, cs.CC, math.OC arXiv: https://arxiv.org/abs/2608.12134v1 We study nonnegative submodular maximization subject to a general matroid when the offline algorithm is given an arbitrary controlled value oracle. Our main result is an adversarial resilience theorem for the Spiteful Greedy Swap Poisson Process (SGS-Poisson): without modifying its Poisson intensity, single-element exchange rule, or spiteful drop step, the algorithm retains limiting approximation factors $1/e$ for non-monotone objectives and $1-1/e$ for monotone objectives. More precisely, under every controlled oracle $\widehat f$ satisfying $|\widehat f(S)-f(S)|\le ξ$ for every set $S$, our implementation returns a feasible set with expected value at least $(1/e-\varepsilon)\OPT-O(kξ)$ and $(1-1/e-\varepsilon)\OPT-O(kξ)$, respectively, using $\widetilde O(nk^2\varepsilon^{-2})$ oracle calls. As a consequence, the offline-to-online reduction yields full-bandit CMAB algorithms for general matroid-constrained submodular rewards with exact limiting approximation-regret factors $1/e$ and $1-1/e$ and $\widetilde O(n^{1/5}k^{4/5}T^{4/5})$ regret. --- ### GUIDE: Governed Unified Intelligence for Document-to-Artifact Generation in Enterprise Settings Authors: Shivali Dalmia, Sumukha Thoppanahalli, Mohammadreza Sediqin, Abhishek Mukherji Published: 2026-08-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.12133v1 Enterprise guideline documents are heterogeneous and multimodal, combining narrative text, complex tables, and embedded images. Existing LLM and VLM systems face hallucinated content, table structure degradation, and lack governed workflows extending beyond extraction to validation and artifact generation. This leaves enterprises to perform this manually, consuming 2-3 days per document. To address this, we introduce GUIDE, a governed multi-agent framework built on a shared versioned rule store with schema-validated inter-agent contracts and end-to-end provenance tracking. Six specialized agents handle parsing, VLM-driven extraction, consistency checking, evaluation, human-in-the-loop (HITL) escalation, and persona-tailored artifact synthesis. Evaluated on 120 real-world enterprise guideline documents, GUIDE achieves 96% document success, extracts 3,896 rules with 71.4% auto-approved, produces 812 deployment-ready artifacts, and reduces turnaround to 40-125 minutes per document. --- ### SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges Authors: Yuchao Wu, Junqin Li, XingCheng Liang, Yongjie Chen, Yinghao Liang, Linyuan Mo, Guanxian Li Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.12129v2 While retrieval-augmented generation (RAG) has proven effective at giving LLMs access to external knowledge, mainstream dense-retrieval implementations remain inherently limited in handling structured constraints and multi-hop reasoning. Graph-based methods address this by constructing knowledge graphs offline, but they often fragment semantics, incur high maintenance, and complicate incremental updates. We propose SAG (SQL-Retrieval Augmented Generation), a structured retrieval architecture that organizes documents into an event-entity index without building a global knowledge graph. SAG represents each chunk as a semantically complete event paired with its entities, forming a latent hyperedge that preserves n-ary relations without decomposing them into triples. At query time, SAG treats shared entities as join keys to connect related chunks. This dynamically yields a query-scoped neighborhood of events, and yet every piece of evidence remains the original chunk throughout. Experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue show that SAG achieves the best retrieval and end-to-end QA performance on every benchmark, with gains that widen as reasoning-chain complexity increases. On MuSiQue, where multi-hop evidence chaining is most demanding, SAG reaches 80.36% Recall@5, outperforming the strongest baseline by 11.52 points. This work paves the way for knowledge infrastructure that enables LLM agents to retrieve and reason over continually growing organizational knowledge. --- ### SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges Authors: Yuchao Wu, Junqin Li, XingCheng Liang, Yongjie Chen, Yinghao Liang, Linyuan Mo, Guanxian Li Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.12129v1 While retrieval-augmented generation (RAG) has proven effective at giving LLMs access to external knowledge, mainstream dense-retrieval implementations remain inherently limited in handling structured constraints and multi-hop reasoning. Graph-based methods address this by constructing knowledge graphs offline, but they often fragment semantics, incur high maintenance, and complicate incremental updates. We propose SAG (SQL-Retrieval Augmented Generation), a structured retrieval architecture that organizes documents into an event-entity index without building a global knowledge graph. SAG represents each chunk as a semantically complete event paired with its entities, forming a latent hyperedge that preserves n-ary relations without decomposing them into triples. At query time, SAG treats shared entities as join keys to connect related chunks. This dynamically yields a query-scoped neighborhood of events, and yet every piece of evidence remains the original chunk throughout. Experiments on HotpotQA, 2WikiMultiHopQA, and MuSiQue show that SAG achieves the best retrieval and end-to-end QA performance on every benchmark, with gains that widen as reasoning-chain complexity increases. On MuSiQue, where multi-hop evidence chaining is most demanding, SAG reaches 80.36% Recall@5, outperforming the strongest baseline by 11.52 points. This work paves the way for knowledge infrastructure that enables LLM agents to retrieve and reason over continually growing organizational knowledge. --- ### SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks Authors: Tao Yu, Yifei Qu, Zhiqing Cui, Pengfei Zhou, Zhongtian Luo, Yujia Yang, Shenghua Chai, Haopeng Jin, Zhenghao Zhang, Xinming Wang, Hongzhu Yi, Wangbo Zhao et al. Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12127v2 Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA evaluation, lacks systematic calibration optimization for open-set scenarios, and employs training objectives that dilute multi-positive signals via softmax normalization without incorporating cost. We address these limitations with three contributions: (1)VLM-ExecRouterBench, the first execution-oriented VLM routing benchmark covering Code, Agentic, and Search domains with 11 candidate models spanning nearly two orders of magnitude in pricing; (2)SCOPE-Router, a dual-tower router that matches queries to model behavior profiles constructed via hybrid calibration (random/diagnostic/diversity sampling), enabling new models to join routing without retraining; (3)CRM+RCCR, an architecture-agnostic cost-aware objective that encodes cost preference into continuous relevance targets through per-pair independent scoring, eliminating multi-positive dilution while regularizing queries with similar routing preferences to be closer in the routing space. Empirically, SCOPE-Router achieves the best Rank Score on all three benchmarks, surpassing the runner-up by 1.84 points under OOD settings and by 6.75 points under doubly OOD open-set evaluation. When applied to four diverse routers, CRM+RCCR improves Rank Score by 1.25--6.21 points. --- ### SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks Authors: Tao Yu, Yifei Qu, Zhiqing Cui, Pengfei Zhou, Zhongtian Luo, Yujia Yang, Shenghua Chai, Haopeng Jin, Zhenghao Zhang, Xinming Wang, Hongzhu Yi, Wangbo Zhao et al. Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12127v1 Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA evaluation, lacks systematic calibration optimization for open-set scenarios, and employs training objectives that dilute multi-positive signals via softmax normalization without incorporating cost. We address these limitations with three contributions: (1)VLM-ExecRouterBench, the first execution-oriented VLM routing benchmark covering Code, Agentic, and Search domains with 11 candidate models spanning nearly two orders of magnitude in pricing; (2)SCOPE-Router, a dual-tower router that matches queries to model behavior profiles constructed via hybrid calibration (random/diagnostic/diversity sampling), enabling new models to join routing without retraining; (3)CRM+RCCR, an architecture-agnostic cost-aware objective that encodes cost preference into continuous relevance targets through per-pair independent scoring, eliminating multi-positive dilution while regularizing queries with similar routing preferences to be closer in the routing space. Empirically, SCOPE-Router achieves the best Rank Score on all three benchmarks, surpassing the runner-up by 1.84 points under OOD settings and by 6.75 points under doubly OOD open-set evaluation. When applied to four diverse routers, CRM+RCCR improves Rank Score by 1.25--6.21 points. --- ### Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation Authors: Akash Kundu, Emanuel Tewolde, Ratip Emin Berker, Samuel F. Brown, Vincent Conitzer Published: 2026-08-12 Categories: cs.GT, cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2608.12125v1 As LLM-based agents with user-instructed goals are becoming widely deployed, they increasingly encounter each other in strategic interactions, and face challenges of finding mutually beneficial outcomes. Prior literature has argued that cooperation problems such as the Prisoner's Dilemma are resolvable in settings where agents know they follow very similar decision making patterns, as for example in monocultural AI ecosystems. Following that line of work, this paper introduces the first framework for evaluating LLM decision making when agents are provided with graded similarity signals. Among our findings, we establish that different LLM models vary drastically in how they navigate similarity signals, with some modern models showing consistent behavior across cooperation problems, payoff structures, and prompt framing. Perhaps surprisingly, our experiments also show that the dataset based on which the similarity signal is computed has small to no impact on induced cooperation, and that LLM models systematically self-identify as highly similar when asked to evaluate another model's chain-of-thought reasoning by themselves. Finally, we develop an LLM-behavioral-game-theoretic model that captures some of their reasoning rationale, and show that it can support cooperative outcomes in equilibrium under sufficiently high similarity scores. --- ### Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Authors: Josef Liyanjun Chen Published: 2026-08-12 Categories: cs.DC, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2608.12123v2 We introduce a mechanism that improves LLM-agent execution: keeping four-byte, GPU-computed control-path routing decisions on-device, avoiding a round-trip to host memory for redispatch. It is faster than host-dispatch in all 36 placements x mechanisms settings in our benchmark across four named GPUs with row-median speedup of 1.19x-2.39x, and outputs are correct, matching an independent host implementation, for all 14,557,440 calls in all configurations, in both tested mechanisms. Agent control paths can be deterministic. Their transitions between LLM calls and external tool calls can be GPU-accelerated by batching across agents and time. We define a cohort of transitions with launch times in a window, and study four shares of GPU-active time: a fixed-partition baseline F, an optimal P*, an upper bound U, and an online result A. Under assumptions of uniform relative launch deadlines, infinite capacity, and zero service times, we compute P* with a custom dynamic program and validate our simulator against it. We replay an anonymized 851-session trace, shown in full as a panel, stationary-ized with a Poisson process. With 100,000 target active agents and a launch deadline of 50 ms, where the headline results have K=256, we find F=30.19%, P*=43.00%, U=45.85%; our method for computing P* reveals that 81.83% of this opportunity is recoverable from cohort packing at fixed window ends. Our method for U relies on a novel notion of route-key, used only as a proxy (via conditional statistics) and does not purport to establish route-equivalence. We find a nested graph that retains some host-side decisions slower in all 60 configurations (five placements). --- ### Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control Authors: Josef Liyanjun Chen Published: 2026-08-12 Categories: cs.DC, cs.AI, cs.OS arXiv: https://arxiv.org/abs/2608.12123v1 LLM-agent services repeatedly execute small deterministic transitions between model and tool calls: route an outcome, update state, and emit the next effect. We ask when this control path exposes enough concurrent work for GPU execution, and what changes when a GPU-computed route decision remains on device. We formalize the ready-cohort boundary using fixed-partition share F, exact offline share P*, local upper bound U, and online achieved share A. Under zero service time, unlimited capacity, and equal relative launch deadlines, a specialized dynamic program computes P* exactly. In a stationary Poisson replay of one pinned 851-session public trace panel, the primary condition at 100,000 target active sessions, K=256, and a 50 ms launch deadline gives F=30.19%, P*=43.00%, and U=45.85%. Exact packing recovers 81.83% of the opportunity lost at fixed window boundaries. The outcome-derived route key is a conditioning proxy, not proof of executable identity. A separate mechanism study keeps a GPU-computed binary decision on device instead of returning four bytes to the host and redispatching. Across four named GPU placements, the device-resident path is faster in all 36 configurations; within-placement row-median ratios range from 1.19x to 2.39x. Across both admissible mechanisms, all 14,557,440 tested batched invocations match a separately implemented host oracle. A fixed nested device graph that removes no host decision is slower in all 60 configurations across five placements. Together, the studies establish two measurable gates for GPU agent control: deadline-feasible cohort supply and observation placement. A joined finite online runtime is required to measure A, CPU displacement, and service-level benefit. --- ### HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing Authors: Zhenjie Yang, Xingyu Jiao, Guopeng Zhong, Shuzhe Yang, Shi Che, Chao Wu, Chenyu Jiang, Dongjie Zhang, Yideng Zhang, Zheng Zhang, Muyun Jiang, Haisheng Su et al. Published: 2026-08-12 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.12122v1 Robotic manipulation with dexterous hands is a cornerstone of Embodied AI, yet its progress is stifled by the high cost of collecting embodiment-aware teleoperation data. While abundant egocentric videos of human hands offer a scalable alternative, the profound discrepancies in appearance, articulation, and camera viewpoints between human and robotic data raise significant challenges for co-training. Though existing general image-editing models demonstrate strong capabilities, they lack necessary embodiment-specific priors to fully bridge this gap. In this work, we present HandEdit, a unified large-scale embodiment-aware image-editing dataset and benchmark specifically designed to transform human hands and arms into various dexterous robotic embodiments within egocentric frames. HandEdit comprises over 200M editing instances derived from five diverse source datasets, covering 26 distinct URDFs, including 13 hand-only and 13 hand-arm configurations. Alongside the dataset, we establish a unified benchmark protocol with two tracks: Hand-only and Hand-Arm, supporting URDF-conditioned evaluation. We conduct extensive evaluations of 11 representative image-editing baselines using a multi-dimensional metric suite, including generic similarity metrics, VLM-based judgment, and embodiment-aware metrics. HandEdit serves as a critical resource at the intersection of image editing and robotics: it advances embodiment-aware editing models while enabling scalable dexterous robotic learning from abundant human video data, paving the way for more generalizable Embodied AI. --- ### QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving Authors: Yilin Liu, Rui Meng, Wangze Ni, Jianxin Yan, Heng Cao, Libin Zheng, Peng Cheng, Jinfei Liu Published: 2026-08-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.12121v1 Retrieval-Augmented Generation (RAG) repeatedly prefills identical text chunks across queries, incurring redundant computations. Position-Independent Caching (PIC) mitigates it by reusing precomputed Key-Value (KV) across positions, but its efficiency is constrained by the large volume of text tokens. Rendering text chunks as images can compress the text into fewer visual tokens, but the rendered-image PIC suffers more severe quality degradation than the text PIC. This representation-specific gap primarily arises from contextual mismatches across independently compiled caches and the loss of fine-grained textual evidence during visual compression. Existing PIC repair methods mainly address the former through selective recomputation, but they incur online computation and cannot recover lost textual details. We propose QV-PIC, a query-aware dual-resolution PIC reuse framework guided by model-native templates. Offline, QV-PIC compiles visual caches under the model's native chat-template prefix, improving PIC quality without online recomputation. Online, it preserves global context with low resolution and restores fine-grained textual evidence within a high-resolution budget by cumulative query relevance scores, retaining the efficiency benefit of visual compression. Across six tasks, QV-PIC improves average F1 by 21.6 points over vanilla rendered-image PIC, closes the gap to vanilla text PIC, and surpasses optimized text PIC by 2.58 F1 while reducing TTFT by 17.2\%. Relative to full prefill, it cuts TTFT by 83.8%. --- ### Attractor Image-Based Deep Learning of Arterial Pulse Waves for Age Classification Authors: Sara Vardanega, Patrick Segers, Philip Aston, Ernst Rietzschel, Jordi Alastruey, Manasi Nandi Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12117v1 Arterial pulse waveform morphology evolves with age, reflecting structural and functional changes in the cardiovascular system. Thus, vascular age is a valuable surrogate marker of cardiovascular health, and premature vascular ageing can indicate increased disease risk. Pulse wave analysis could support risk stratification in otherwise asymptomatic adults. We transformed pulse wave time-series data from photoplethysmography (PPG) and arterial tonometry into images, using the Symmetric Projection Attractor Reconstruction (SPAR) method. These SPAR images were used to train a convolutional neural network to classify healthy subjects into two closely spaced age groups (35-40 and 50-55 years). The model demonstrated consistent classification performance across internal and external test sets, achieving F1 scores above 70% for both PPG and tonometry signals. These results suggest that SPAR-derived pulse wave images contain discriminative morphological features even among healthy adults close in age. This proof-of-concept lays the groundwork for future research into the use of SPAR for early risk detection using smart wearables. --- ### Structuring the Space of Perspectives Authors: Agnese Daffara, Sebastian Padó, Tanise Ceron Published: 2026-08-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.12113v1 The same event can be reported from different perspectives depending on the experiences, background, and beliefs of the writer or speaker. A variety of NLP areas engage with perspectives, spanning from text analysis to algorithm optimization. A wide range of operative concepts (such as stances, sentiment, frames, and arguments) has been used to capture perspectives in texts, however the precise relationships among those concepts remain unclear. Arguably, a deeper theoretical understanding of these concepts would empower more effective research on perspectives. In this paper, we address this gap by reviewing the space of perspectives in NLP and defining a set of properties that help distinguishing perspective-related concepts. Our analysis leads us to posit a hierarchy which organizes these concepts linearly along a single axis. Finally, we show how this principled conceptual hierarchy can help researchers navigate the field and select operationalizations of perspective that align with their specific research objectives. --- ### The Advective Fisher-Rao Geometry of Deterministic Measure Transport Authors: Benjamin Gess, Johannes Müller Published: 2026-08-12 Categories: math.OC, cs.LG, math.DG, math.PR arXiv: https://arxiv.org/abs/2608.12111v1 A novel advective Fisher-Rao metric is introduced for optimization tasks on paths of probability measures governed by the continuity equation. This metric is shown to lead to optimal descent directions. It is then shown that this metric arises naturally from three different perspectives: As the rescaled zero-noise limit of the Fisher-Rao metric on path measures, as the expected value of the second variation of the Freidlin--Wentzell large deviation rate functional, and as the Hessian of the Benamou--Brenier action functional from dynamic optimal transport. We supplement this geometric construction with computational experiments. Here, we demonstrate empirically that the advective Fisher-Rao metric yields the desired optimal fitting of probability densities, whereas the Gauss--Newton method yields optimal fitting of velocity fields. --- ### Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning Authors: Mirko Konstantin, Stefan Zachow, Anirban Mukhopadhyay Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12108v2 Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are beneficial for aggregation with respect to each client's target domain. Existing methods typically address this problem in parameter space by comparing model parameters or gradients. However, parameter-space similarity can be a poor proxy for predictive behavior, especially under heterogeneous, non-IID data. Consequently, updates that are misaligned with a client's target domain, including those caused by heterogeneous data or malfunctioning clients, may degrade local model performance. We propose Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space. LIGHTYEAR uses an NTK-based agreement score to characterize predictive behavior and determine a personalized aggregation set for each client. By relating model parameters to local predictive responses, the Neural Tangent Kernel (NTK) provides a more expressive criterion for update selection than parameter-space similarity alone. Because function-space information is not available before aggregation in conventional centralized FL, LIGHTYEAR uses a peer-to-peer (P2P) topology in which clients exchange updates directly and evaluate incoming models on private validation data. Each client selects only updates that are beneficial for its own target domain and aggregates them using a regularized rule that improves stability under heterogeneity. Across five datasets and nine baseline methods, LIGHTYEAR consistently outperforms centralized FL baselines and existing P2P approaches. --- ### Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning Authors: Mirko Konstantin, Stefan Zachow, Anirban Mukhopadhyay Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12108v1 Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are beneficial for aggregation with respect to each client's target domain. Existing methods typically address this problem in parameter space by comparing model parameters or gradients. However, parameter-space similarity can be a poor proxy for predictive behavior, especially under heterogeneous, non-IID data. Consequently, updates that are misaligned with a client's target domain, including those caused by heterogeneous data or malfunctioning clients, may degrade local model performance. We propose Local Inference Guided Aggregation for Heterogeneous Training Environments to Yield Enhancement Through Agreement and Regularization (LIGHTYEAR), a federated learning framework that performs update selection in function space. LIGHTYEAR uses an NTK-based agreement score to characterize predictive behavior and determine a personalized aggregation set for each client. By relating model parameters to local predictive responses, the Neural Tangent Kernel (NTK) provides a more expressive criterion for update selection than parameter-space similarity alone. Because function-space information is not available before aggregation in conventional centralized FL, LIGHTYEAR uses a peer-to-peer (P2P) topology in which clients exchange updates directly and evaluate incoming models on private validation data. Each client selects only updates that are beneficial for its own target domain and aggregates them using a regularized rule that improves stability under heterogeneity. Across five datasets and nine baseline methods, LIGHTYEAR consistently outperforms centralized FL baselines and existing P2P approaches. --- ### Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars Authors: Ruibin Li, Tao Yang, Zhiyuan Ma, Fangzhou Ai, Shilei Wen, Lei Zhang Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12107v1 Existing streaming video systems often rely on sequential, distillation-centered training pipelines to enable few-step long-video generation. However, this paradigm suffers from two limitations. First, failures or distribution shifts introduced in earlier stages affect later optimization, complicating the training process to converge. Second, the distillation-centric objective favours short-term generation but is prone to quality degradation when autoregressive errors accumulate over long rollouts. We propose Avatar-Forever, a decoupled parallel training framework for high-quality real-time infinite interactive avatars. Instead of coupling generation efficiency and long-horizon robustness under a sequential distillation pipeline, we treat them as two independent capabilities that can be trained in parallel. One branch performs full-parameter distillation to train an efficient generator with high visual quality, while another trains a lightweight long-horizon adapter via Recovery-oriented Rollout Training (RRT), which improves generation robustness under long-horizon inference conditions. Our decoupled parallel training design simplifies the overall training process and avoids unnecessary objective conflicts between few-step generation and long-horizon adaptation. We further introduce ForeverCache, a chunk-wise feature caching mechanism to substantially reduce redundant history computation during streaming inference. Built upon a 22B video foundation model, Avatar-Forever supports unbounded audio-driven avatar generation while maintaining identity consistency, motion coherence, and visual fidelity, enabling an end-to-end throughput of high-resolution 768x512 videos at 27.2 FPS on a single H100 GPU and providing a practical path toward stable digital humans. --- ### No One to Blame: A Framework of Constitutive AI Unaccountability Authors: Long Hoang Nguyen, Eva Späthe, Sebastian Lins, Ali Sunyaev Published: 2026-08-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.12104v2 The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms. Existing research predominantly frames AI accountability gaps as barriers that can be overcome through better standards, transparency, and institutional reform. We argue that this framing is insufficient: certain configurations of actors, systems, and institutions render AI accountability conceptually unachievable regardless of effort. We introduce the concept of constitutive AI unaccountability to capture these configurations. Through a three-stage qualitative study comprising a concept-centric literature analysis, a secondary analysis of 27 expert interviews with AI professionals from technical, legal, and sociotechnical backgrounds, and an illustrative framework application to the open-source agentic AI system OpenClaw, we identify nine categories and 20 themes of constitutive AI unaccountability. These are organized across structural, technological, and normative clusters and reinforce one another through eight directed interdependencies. Our framework is operationalized as a diagnostic instrument of 20 questions, which detected 17 of 20 conditions when applied to OpenClaw, including an inverted anthropomorphism configuration in which the AI agent was the only identifiable actor. We contribute a reframing of AI unaccountability as a constitutive property of sociotechnical systems, an extension of the four barriers to accountability, and a practical instrument for identifying accountability voids in specific AI deployments. --- ### No One to Blame: A Framework of Constitutive AI Unaccountability Authors: Long Hoang Nguyen, Eva Späthe, Sebastian Lins, Ali Sunyaev Published: 2026-08-12 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2608.12104v1 The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms. Existing research predominantly frames AI accountability gaps as barriers that can be overcome through better standards, transparency, and institutional reform. We argue that this framing is insufficient: certain configurations of actors, systems, and institutions render AI accountability conceptually unachievable regardless of effort. We introduce the concept of constitutive AI unaccountability to capture these configurations. Through a three-stage qualitative study comprising a concept-centric literature analysis, a secondary analysis of 27 expert interviews with AI professionals from technical, legal, and sociotechnical backgrounds, and an illustrative framework application to the open-source agentic AI system OpenClaw, we identify nine categories and 20 themes of constitutive AI unaccountability. These are organized across structural, technological, and normative clusters and reinforce one another through eight directed interdependencies. Our framework is operationalized as a diagnostic instrument of 20 questions, which detected 17 of 20 conditions when applied to OpenClaw, including an inverted anthropomorphism configuration in which the AI agent was the only identifiable actor. We contribute a reframing of AI unaccountability as a constitutive property of sociotechnical systems, an extension of the four barriers to accountability, and a practical instrument for identifying accountability voids in specific AI deployments. --- ### Confidence Calibration of Deep Learning Systems Authors: Coby Penso Published: 2026-08-12 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.12100v1 In high-stakes applications, reliable confidence estimates are as important as the predictions themselves. Confidence calibration ensures that predicted probabilities reflect the likelihood of correctness, making it essential for safe deployment of deep learning models. However, existing methods typically assume access to clean validation data, which is often unrealistic due to label noise and domain shifts. This thesis develops methods for improving calibration under these conditions. First, we address calibration under label noise. Standard methods can produce misleading confidence estimates when labels are unreliable. We propose a framework that uses an estimated noise model to reconstruct noise-free confidence estimates by modeling the relationship between noisy and clean label distributions. We extend this approach to Conformal Prediction (CP), which provides set-valued predictions with guaranteed coverage. Our noise-aware CP method estimates clean conformity scores despite label noise, enabling reliable uncertainty quantification. Next, we study calibration in unsupervised domain adaptation, where a model trained on a labeled source domain is adapted to an unlabeled target domain. Since labeled target data are unavailable, we estimate target-domain accuracy from source performance and domain discrepancies, enabling calibration without target labels. We also consider privacy-preserving settings in which user labels and model outputs must remain protected. We propose a locally differentially private conformal prediction framework that provides valid uncertainty quantification while maintaining privacy guarantees and balancing privacy, computational feasibility, and prediction reliability. Our results bridge calibration theory and practical deployment in safety-critical applications, contributing to reliable, privacy-preserving, and noise-resilient neural network predictions. --- ### RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation Authors: Rong Chao, Sung-Feng Huang, Moreno La Quatra, Sabato Marco Siniscalchi, Wen-Huang Cheng, Szu-Wei Fu, Yu Tsao Published: 2026-08-12 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2608.12099v2 We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectures that rely on a growing key-value cache, Mamba propagates a fixed-size recurrent state per layer, enabling memory- and bandwidth-efficient long-form inference. We further introduce a progressive knowledge distillation (KD) strategy that compresses an 8-layer teacher into a shallow 1-layer student by jointly distilling complex spectral outputs and intermediate representations. On Voicebank-DEMAND, the 8-layer RT-SEMamba achieves 3.32 PESQ with a 25 ms algorithmic latency constraint, and the distilled 1-layer student improves over a naive 1-layer baseline from 3.06 to 3.18 PESQ while preserving the same steady-state RTF, delivering a 2.64x speedup over the teacher. These results demonstrate that state-space models with progressive KD provide a competitive quality-latency trade-off for real-time SE. --- ### RT-SEMamba: Real-Time Speech Enhancement Mamba via Progressive Knowledge Distillation Authors: Rong Chao, Sung-Feng Huang, Moreno La Quatra, Sabato Marco Siniscalchi, Wen-Huang Cheng, Szu-Wei Fu, Yu Tsao Published: 2026-08-12 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2608.12099v1 We present RT-SEMamba, a fully causal speech enhancement (SE) model built upon causal time-frequency Mamba blocks. Unlike Transformer-based architectures that rely on a growing key-value cache, Mamba propagates a fixed-size recurrent state per layer, enabling memory- and bandwidth-efficient long-form inference. We further introduce a progressive knowledge distillation (KD) strategy that compresses an 8-layer teacher into a shallow 1-layer student by jointly distilling complex spectral outputs and intermediate representations. On Voicebank-DEMAND, the 8-layer RT-SEMamba achieves 3.32 PESQ with a 25 ms algorithmic latency constraint, and the distilled 1-layer student improves over a naive 1-layer baseline from 3.06 to 3.18 PESQ while preserving the same steady-state RTF, delivering a 2.75x speedup over the teacher. These results demonstrate that state-space models with progressive KD provide a competitive quality-latency trade-off for real-time SE. --- ### Graph-Structured Rubrics: Compiling Rubrics into Typed Evaluation Graphs for LLM Judges Authors: Xi Chen, Jie Mu, Mo Xuan, Qun Shao Published: 2026-08-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.12097v1 Rubric-based evaluators commonly treat rubrics as prompt context or flat criteria: they specify what to judge but leave criterion composition implicit, even when natural-language rules state it. We introduce Graph-Structured Rubrics (GSR), which compiles a rubric into a response-independent typed evaluation graph before observing responses. Criterion nodes elicit judgments; transformation, reduction, and gating operators compose them through named ports; and a task-specific output mapping, termed Readout, converts the unique sink into a score or preference. Compilation rejects malformed or type-incompatible graphs. Pointwise evaluation judges rubric dimensions separately before graph aggregation; pairwise evaluation reuses the graph with one judgment for each candidate under every criterion. Under GPT-OSS-120B, GSR improves exact score agreement by 0.62--6.75 percentage points over Prometheus-style scoring on four pointwise datasets and achieves the numerically highest end-to-end pairwise accuracy on two preference benchmarks under native tie and abstention policies. --- ### Task- and dataset-specific information in protein language models Authors: Roman Joeres, Ilya Senatorov, Anastasia Kolchina, Dietrich Klakow, Olga V. Kalinina Published: 2026-08-12 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2608.12090v4 Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs). By consensus, embeddings from the models' last layers are used, while the models' internal behavior remains poorly understood. We analyzed 13 PLMs across 15 DTs and 9 datasets to assess the value of embeddings from intermediate PLM layers. We trained probe models on embeddings from each layer, compared their performance, and showed that the last layers of PLMs rarely produced embeddings that led to the best results on downstream tasks. Furthermore, we identified a connection between how models learn a certain DT and the similarity between that DT and the pre-training objective. For example, for residue-level downstream tasks, we observed a steady increase in performance across almost all PLM layers, which we attributed to their similarity to most PLMs' pre-training objectives. To allow the community to capitalize on our findings, we provide PLMSommelier, a Python package that automatically identifies the best PLM layer for a given DT with ~98% accuracy and creates a truncated model using only the early layers up to the best-performing layer. This will help users save time and memory during inference and yield better predictive performance. --- ### Task- and dataset-specific information in protein language models Authors: Roman Joeres, Ilya Senatorov, Olga V. Kalinina Published: 2026-08-12 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2608.12090v1 Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs). By a common consensus, embeddings from the model's last layer are used, and the model's internal behavior remains poorly understood. We analyzed 13 PLMs across 15 DTs from 11 datasets to investigate the informativeness of embeddings created in intermediate PLM layers. We trained probe models on embeddings from each layer, compared their performance, and computed characteristics of the latent spaces they span to estimate the information they contain, and found that the last layers of PLMs rarely contained embeddings that led to the best results on downstream tasks. Furthermore, we identified a connection between DTs and the distribution across PLMs' layers of the relevant information to predict that task. For example, similarity between the pre-training objective and the objective of predicting properties of individual residues leads to a steady increase in understanding of such tasks across the layers of PLMs. On the other hand, for whole-protein tasks, we observe that the dataset, rather than the task itself, defines PLMs' ability to perform well on a DT. Embeddings from shallow layers of PLMs perform better for datasets that contain deep mutational scan (DMS) data, while datasets containing diverse natural proteins find most useful embeddings in the models' deeper layers. Additionally, we discover that the performance of PLMs drops significantly when tasks are introduced for artificial proteins. --- ### RA-ClipScore: Making Generative Model Evaluation More Interpretable Authors: Yifan Lu, Taras Kucherenko, Hedvig Kjellström, Judith Bütepage Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12088v1 Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventional metrics such as FID provide only scalar scores with limited diagnostic insight. Widely adopted CLIP-based metrics enable semantic evaluation beyond simple training class labels, but inherit limitations from CLIP's training paradigm that restrict attribute-wise analysis. We propose RA-CLIPScore, a novel metric that mitigates these issues and extends CLIP-based evaluation to spatial distribution alignment, measuring whether generated objects adhere to the positional priors found in the training data. RA-CLIPScore introduces dual prompts to decouple competing attributes and leverages local patch tokens to capture fine-grained regional semantics. We evaluate image generative models on their ability to match both attribute and spatial distributions of the training data. Extensive experiments show that RA-CLIPScore provides more robust and interpretable evaluations than prior methods, particularly under distribution misalignment or partially irrelevant textual attributes. We further demonstrate how it reveals spatial biases in generative models. User evaluations confirm that Regional Single Attribute Divergence based on our RA-CLIPScore aligns more closely with human perception of visual diversity than existing semantic metrics. --- ### Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP Authors: Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina, Théo Sourget Published: 2026-08-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.12086v1 Vision-language models, such as contrastive language-image pre-training (CLIP)-based approaches, have reached state-of-the-art (SOTA) results in medical artificial intelligence. However, recent work reveals that CLIP-based models remain vulnerable to shortcuts. We investigate how real-world shortcuts manifest across different layers of the medical CLIP-based model, MedCLIP, and its vision encoder, a frozen ResNet-50. We attach 17 linear classification probes to the intermediate layers of the ResNet-50 and train them on three different dataset configurations and targets: NIH-CXR14 (pneumothorax) and PadChest (cardiomegaly and pneumothorax). This setup allows us to observe model behaviour during evaluation using subgroup-based calibration and layer-wise confidence curves. We find that the final linear probes achieve a high AUROC but poor calibration in the models. The layer-wise confidence analyses suggest that shortcuts emerge at different depths. Patterns consistent with localised shortcuts, such as drains, appear at later layers, while patterns consistent with diffuse shortcuts, such as scanner-specific noise patterns, emerge earlier, aligning with previous work. Finally, we conduct a manual analysis of the images, which reveals data quality issues in both NIH-CXR14 and PadChest. Our findings underscore that even SOTA models remain vulnerable to shortcuts, and the need for high-quality and well-annotated datasets to draw solid conclusions. Code can be found on our GitHub: https://github.com/nikodice4/MedCLIP_shortcuts. --- ### NAE: Normalizing AutoEncoder Authors: Muhammad Abdur Rafae, Niels Landwehr Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12084v1 We consider the setting of Normalizing flows with approximate inverses, an established paradigm spanning both full-dimensional ($d=D$) and bottleneck ($d<D$) settings, and group these models under the term flow autoencoders. We present a theoretical investigation into their training dynamics and prove that the proposed loss used by existing approaches is suboptimal; specifically, both encoder and decoder surrogates must be optimized in alignment with reconstruction loss. Guided by these insights, we propose Normalizing Autoencoder (NAE), which employs a novel conditional loss that aligns the surrogate loss gradient with that of reconstruction loss, directly improving upon the current standard. Extensive experiments across molecule generation, tabular data, and image benchmarks demonstrate that NAE achieves state of the art performance. Our work highlights the importance of loss alignment in flow autoencoders and establishes NAE as a powerful generative framework. --- ### Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversion Authors: David Bechtoldt, Sidney Bender Published: 2026-08-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.12083v1 Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network analysis, yet they provide no intrinsic explanation of their predictions. This limits their adoption in high-stakes and safety-critical settings. Counterfactual explanations address this by revealing the minimal structural modifications that would change a model's prediction. On graphs, however, such a modification is hard to produce. The search space is discrete and combinatorial, and a valid answer must respect categorical node and edge types together with domain rules such as chemical valency in the case of molecular graphs. Existing explainers give up one of two things. Either edits are not held on the data manifold, or the search does not span the full edit space. We propose Graph Diffusion Counterfactual Explanation via Inversion (GDCE-I), which gives up neither. A discrete denoising diffusion model with a novel discrete inversion scheme enables distribution-aware edits leveraging the whole domain edit space. We further address the incomplete and inconsistent evaluation of graph counterfactuals by deriving a framework of explanation desiderata and applying it to every method under one shared protocol. Across four benchmarks, GDCE-I outperforms related work by a large margin on the defined framework. For the molecular domain, we further qualitatively show that GDCE-I attains interpretable in-distribution solutions. --- ### Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models Authors: Shukrullo Nazirjonov, Sai Prasanna, Anna Manasyan, Georg Martius Published: 2026-08-12 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.12078v1 Learning world models from offline trajectories enables agents to accomplish different tasks through planning. Object-centric (OC) representations, which decompose a scene into a set of slots that bind to its objects, have been proposed as an inductive bias for world models that are more sample-efficient and generalize better. Yet prior object-centric world models (OCWMs) take the slot encoder as given and evaluate only in-distribution, leaving open whether the object-centric bias actually delivers for planning and what within the OCWM drives it. We conduct a controlled study of OCWMs for visual model-predictive control along two axes: object-centric representation quality and generalization under distribution shift relative to scene-centric models. We find that (i) planning success correlates positively with unsupervised slot-quality metrics (FG-ARI, mBO), though the gains saturate at high slot quality; (ii) with well-bound slots, the auxiliary proprioception inputs and masking inductive bias that prior methods relied on become unnecessary; and (iii) under unseen distribution shifts, the OCWM with well-bound slots is more robust overall than the end-to-end trained scene-centric LeWM, while DINO-WM, built on similar frozen pretrained features, remains competitive -- pointing to pretrained features as a key contributor to robustness. --- ### Draw This First Authors: Dazhi Zhong, Rowan Bradbury, Grant Davis Published: 2026-08-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.12064v1 We invert the typical formulation of sketch generation: instead of drawing strokes in order, we predict a 2D field that defines the order in which strokes are drawn. We use a pretrained latent flow-matching transformer to supply the image prior to predict an intermediate representation, while training the VAE's decoder to predict the order field, stroke mask, and stroke segmentation. We vectorize the predicted segmentation into polylines and sort them by the field, producing an ordered vector sketch. Our model can predict an ordered vector sketch from a text description or derender an image into ordered vectors; for either, it follows text instructions specifying the order of drawing. --- ### Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL Authors: Martin Schuck, Maks Sorokin, Simone Manni, Duy Ta, Angela P. Schoellig, Marco Hutter, Simon Le Cleac'H, Jan Brüdigam Published: 2026-08-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.12063v1 Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping. To bypass this limitation, we leverage Sample-based Model Predictive Control (SMPC) entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets. Because this data solves the fundamental exploration problem, we can train an off-policy RL agent using purely sparse task rewards, drastically reducing the time required to learn new skills and eliminating the need for manual tuning. Integrating this high-level agent with a low-level dynamic stability controller yields more optimal behaviors that strictly align with true task objectives, ultimately allowing the learned policies to surpass the original optimal control teacher. We validate the robustness of this sim-to-real framework by successfully deploying complex loco-manipulation skills across different morphologies, including an arm-equipped Spot quadruped and a G1 humanoid. --- ### Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations Authors: Lior Baruch, Moshe Butman, Kfir Bar, Doron Friedman Published: 2026-08-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.12062v2 Developing dialogue systems capable of engaging in multi-turn, goal-oriented conversations remains a significant challenge, especially in specialized domains with limited data. This research proposes a novel framework called Preference Tree Optimization (PTO), designed to iteratively improve agent models in such dialogue systems, by generating preference data using a method called Preference Tree with Look-Ahead. Focusing on Motivational Interviewing (MI) -- a counseling technique aimed at facilitating behavioral change -- we leverage virtual patients and an oracle evaluator to simulate conversations and generate rich preference datasets. By combining this method with Direct Preference Optimization (DPO), we aim to enhance the agent's decision-making capabilities over iterative training cycles. The proposed framework addresses data scarcity and advances the development of more nuanced and effective dialogue systems in goal-oriented domains. Experimental evaluations demonstrate that the PTO framework enhances dialogue agents' performance in goal-oriented conversations within the domain of Motivational Interviewing (MI). Models trained with PTO consistently outperformed the baseline in key metrics such as session satisfaction and working alliance. Additionally, incorporating look-ahead simulations led to improved long-term planning and more effective conversational strategies, with deeper look-ahead configurations yielding the most stable and high-scoring results. --- ### Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations Authors: Lior Baruch, Moshe Butman, Kfir Bar, Doron Friedman Published: 2026-08-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.12062v1 Developing dialogue systems capable of engaging in multi-turn, goal-oriented conversations remains a significant challenge, especially in specialized domains with limited data. This research proposes a novel framework called Preference Tree Optimization (PTO), designed to iteratively improve agent models in such dialogue systems, by generating preference data using a method called Preference Tree with Look-Ahead. Focusing on Motivational Interviewing (MI) -- a counseling technique aimed at facilitating behavioral change -- we leverage virtual patients and an oracle evaluator to simulate conversations and generate rich preference datasets. By combining this method with Direct Preference Optimization (DPO), we aim to enhance the agent's decision-making capabilities over iterative training cycles. The proposed framework addresses data scarcity and advances the development of more nuanced and effective dialogue systems in goal-oriented domains. Experimental evaluations demonstrate that the PTO framework enhances dialogue agents' performance in goal-oriented conversations within the domain of Motivational Interviewing (MI). Models trained with PTO consistently outperformed the baseline in key metrics such as session satisfaction and working alliance. Additionally, incorporating look-ahead simulations led to improved long-term planning and more effective conversational strategies, with deeper look-ahead configurations yielding the most stable and high-scoring results. --- ### Towards Truly Unsupervised Evaluation of Feature Selection -- Extended Version Authors: Hafiz Saud Arshad, Muhammad Rajabinasab, Arthur Zimek Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12057v4 Feature selection is one of the most important and fundamental tasks in data mining, tackled by a family of methods with an established set of evaluation techniques to measure the quality of a specific method. Most of the methods commonly used for the unsupervised evaluation of feature selection algorithms suffer from critical design flaws which question their unsupervised nature. In this paper, we provide a critical discussion on the established allegedly unsupervised evaluation techniques, and shed light on the reasons why they are not truly unsupervised but, at best, supervised evaluation under an unsupervised downstream task. We also propose a novel, truly unsupervised evaluation framework to measure the quality of the feature selection algorithms without any form of information about the labels. The proposed framework utilizes unsupervised Principal Component Analysis, and optimal transport to measure the quality of the feature selection methods in a truly unsupervised manner. --- ### Towards Truly Unsupervised Evaluation of Feature Selection Authors: Hafiz Saud Arshad, Muhammad Rajabinasab, Arthur Zimek Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12057v1 Feature selection is one of the most important and fundamental tasks in data mining, tackled by a family of methods with an established set of evaluation techniques to measure the quality of a specific method. Most of the methods commonly used for the unsupervised evaluation of feature selection algorithms suffer from critical design flaws which question their unsupervised nature. In this paper, we provide a critical discussion on the established allegedly unsupervised evaluation techniques, and shed light on the reasons why they are not truly unsupervised but, at best, supervised evaluation under an unsupervised downstream task. We also propose a novel, truly unsupervised evaluation framework to measure the quality of the feature selection algorithms without any form of information about the labels. The proposed framework utilizes unsupervised Principal Component Analysis, and optimal transport to measure the quality of the feature selection methods in a truly unsupervised manner. --- ### Do Not Forget the Obvious - RISC: A Risk-Informed Slice-Coverage Protocol for Safe Autonomous Driving Authors: Fabian Hüger Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12051v1 Aggregate metrics may not fully reflect performance in insufficiently examined high-risk driving conditions. We propose RISC (Risk-Informed Slice Coverage), a practical protocol for risk-guided stress testing and coverage-qualified evaluation. Risk-guided stress testing directs a finite audit budget toward risk-relevant sub-datasets, called risk slices, while coverage-qualified evaluation reports results together with explicit statements about which slices are sufficiently or insufficiently covered. The protocol translates safety concerns into machine-readable risk slices, uses lightweight signals to tag candidate data, selects a compact audit set by risk, and qualifies the results using coverage evidence. An LLM can optionally support this process by surfacing relevant but potentially overlooked conditions during test planning, thereby helping engineers not to forget the obvious. RISC is model-agnostic and can be applied to perception modules, driving models, and other autonomous-driving subsystems. We instantiate the protocol for monocular pedestrian perception using 1,000 frames from the Zenseact Open Dataset, image statistics, and a YOLO-based detector proxy. In this proof-of-concept study, risk-guided selection increases critical failure discovery from 34.0% under random sampling to 98.5%. RISC provides a lightweight, assurance-oriented evaluation layer that complements scenario categorization, coverage assessment, and broader testing-and-verification workflows. --- ### Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation Authors: Yungeng Liu, Xuanzi Fang, Yuge Zhang, Shuqi Ren, Haijin Zeng, Yongyong Chen Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12050v1 Kolmogorov--Arnold Networks (KANs) introduce explicit functional representations by parameterizing each network edge as a learnable univariate function. However, existing KAN-based segmentation models optimize edge functions only through objectives defined after edge aggregation, leaving individual functions without an explicit pre-aggregation learning target. To address this limitation, we propose Function-Space Joint-Embedding Predictive Learning (FS-JEPA) for medical image segmentation. Our FS-JEPA framework moves predictive learning into the pre-aggregation function space of KANs. A masked online branch predicts structured signatures of sampled KAN edge functions generated by a full-context exponential moving average target branch, while shared edge indices preserve correspondence between predictions and targets. Rather than predicting an isolated edge response, we represent each sampled edge function using a multi-radius signature composed of function evaluations around its input anchor. This structured representation captures local functional variations that cannot be characterized by a single response and provides a more informative predictive target. The function-space objective is jointly optimized with the segmentation loss during training, while the predictive branch is removed at inference. Experiments on five medical image segmentation benchmarks show that our FS-JEPA achieves the best average Dice and outperforms the strongest competing KAN-based method by +2.25 percentage points. --- ### Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection Authors: Sara Abdulaziz, Abdulrahman Al-Abri, Giacomo D'Amicantonio, Egor Bondarev Published: 2026-08-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.12045v1 Despite growing interest in weakly supervised video anomaly detection (WSVAD), current methods struggle to bridge the gap between coarse temporal supervision and fine-grained spatial reasoning. A key obstacle is the tendency of temporal detectors to latch onto background and scene-level cues rather than truly discriminative anomaly evidence. This background bias raises ethical concerns: models may inadvertently associate anomalies with societal or environmental context rather than authentic crime-related cues. Without spatial grounding, such biases remain hidden and unauditable. To address this, we propose SST-WSVADL, a sparse spatio-temporal framework that bridges temporal anomaly detection with fine-grained spatial localization. Rather than processing all spatial regions indiscriminately, SST-WSVADL progressively focuses on the most anomaly-relevant spatio-temporal regions through dynamic sparsification, naturally suppressing background dominant content while preserving discriminative evidence. The temporal and spatial branches are coupled end-to-end via motion-aware regularization that guides sparsification toward dynamically informative regions, without relying on external detectors or vision-language prompts. We publicly release frame-level spatial annotations and a method-agnostic evaluation protocol for three public datasets: UCF-Crime, XD-Violence, and MSAD. These resources enable the community to audit spatial biases in WSVAD predictions, supporting progress toward more ethical and accountable anomaly detection. Experiments demonstrate that SST-WSVADL is competitive with prior methods across benchmarks while enabling localization and patch-level auditability of scene bias, providing a reproducible foundation for interpretability-oriented evaluation of WSVAD models. --- ### Direct Acceleration of Stochastic Root-Finding Without Variance Reduction and Regularization Authors: TaeHo Yoon, Nicolas Loizou Published: 2026-08-12 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2608.12043v1 Acceleration for deterministic root-finding problems has been extensively studied in recent years; specifically, the anchor-based, or Halpern-type methods achieve optimal convergence rates with respect to the operator norm. However, acceleration via these methods does not directly carry over to stochastic setting due to accumulation of errors, unless one enforces diminishing variance via increasing batch sizes or variance reduction techniques. In this work, we show that another class of acceleration, namely the dual-anchor mechanism, extends to the stochastic setting without such error accumulation, in contrast to anchor-based algorithms. Consequently, we cleanly achieve $O(ε^{-3})$ complexity with iteration-independent batch size, without any variance reduction or double-loop recursive regularization, for stochastic root-finding (resp. fixed-point) problems with cocoercivity (resp. square-nonexpansivity) in expectation. For strongly monotone operators, the same algorithm attains a sharper $\widetilde{O} (ε^{-2})$ complexity, nearly matching the lower bound in terms of $ε$-dependence. --- ### Clustered Randomized Smoothing for Stochastic Prediction Functions Authors: Eduardo Figueiredo, Frederik Mathiesen, Julian Schumann, Jens Kober, Arkady Zgonnikov, Luca Laurenti Published: 2026-08-12 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2608.12037v1 Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions $-$ a critical requirement in safety-critical domains. Randomized smoothing is a leading technique for improving robustness, particularly against adversarial perturbations. Yet, in stochastic multi-modal regression settings, randomized smoothing often fails due to mode collapse, yielding averaged predictions that do not reflect the underlying distribution. To address this limitation, we propose clustered $α$-smoothing, a framework that (1) partitions noisy samples using an arbitrary clustering algorithm, (2) applies $α$-smoothing locally within each cluster, and (3) combines the resulting predictions into a mixture distribution. By interpreting the smoothing distribution as a mixture of $α$-smoothers, we derive a lower bound on the probability that the smoothed prediction lies within a union of compact regions corresponding to distinct modes. We empirically evaluate our framework on two benchmarks, demonstrating substantial improvements over state-of-the-art methods. In stochastic trajectory prediction on a driving simulator dataset, our approach achieves, on average, a $27\%$ lower Wasserstein distance to the ground-truth distribution compared to $α$-smoothing. In quadrotor control, where modes correspond to distinct feasible paths to a target, our method reduces the collision rate by $81\%$ relative to the state-of-the-art randomized smoothing. --- ### Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence Authors: Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Xin Xu, Yunzhi Yao, Dan Zhang, Fei Shen et al. Published: 2026-08-12 Categories: cs.AI, cs.CL, cs.HC, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.12036v3 AI models are increasingly used in scientific discovery and human decision-making. Yet how AI models work and what risks they pose remain poorly understood. As AI development becomes faster and more automated, research on the mechanisms underlying AI remains largely manual. To bridge this gap, we introduce Mechanist, an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI. To ground novel mechanism hypotheses, we construct a scientific knowledge graph of 13,000 studies on AI mechanisms, alongside a multidisciplinary database of 43 million papers spanning 26 fields. For reliable experiment execution, we curate a library of 32 foundational methods for mechanism analysis. Compared with Claude Code and existing AI-scientist systems, Mechanist generates higher-quality mechanism hypotheses and executes experiments more reliably. Across four case studies, Mechanist autonomously discovers new model behaviors and their underlying mechanisms, and translates these discoveries into mechanism-guided interventions and interdisciplinary design. Specifically, Mechanist first uncovers a counterintuitive safety risk in scientific laboratories, showing that unsafe traits can transfer to fine-tuned student models through apparently safe training data and emerge across modalities. Mechanist then develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretraining. Building on this theory, Mechanist develops targeted interventions that improve model performance across diverse scenarios. Finally, Mechanist can also advance interdisciplinary discovery through mechanistic design, providing an alternative to the computationally intensive generate-and-rerank paradigm. --- ### Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence Authors: Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Zhixiang Cui, Xin Xu, Yunzhi Yao, Buqiang Xu et al. Published: 2026-08-12 Categories: cs.AI, cs.CL, cs.HC, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.12036v1 AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood. As AI development becomes faster and increasingly automated, mechanistic exploration remains largely manual, widening the gap between what models can do and our ability to understand and control them. To bridge this gap, we introduce Mechanist, an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI intelligence. To support autonomous mechanistic discovery, we construct an interpretability-focused knowledge graph of approximately 13,000 papers and integrate it with a multidisciplinary database of 43 million papers spanning 26 fields. We further curate a library of 32 foundational methods for mechanism analysis, causal intervention, and validation. Compared with Claude Code and existing AI-scientist systems, Mechanist generates more valuable mechanism hypotheses and executes experiments more reliably. Mechanist also demonstrates a progression from discovering model behaviors to explaining and controlling AI models. Specifically, Mechanist first uncovers a counterintuitive safety risk in scientific laboratories, showing that unsafe traits can transfer across modalities through apparently safe training data. Mechanist then develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretraining. Finally, Mechanist translates these mechanistic insights into practical interventions that improve model performance across diverse scenarios and steer scientific foundation models toward generating DNA sequences with specified properties. --- ### How Far from Clinical Deployment? Evaluating the Complete Unsupervised Domain Adaptation Pipeline in Medical Imaging Authors: Yiheng Xiong, Luisa Gallée, Daniel Santak Wolf, Heiko Hillenhagen, Michael Götz Published: 2026-08-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.12035v1 Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the deployment (target) domain is unlabeled, so models cannot be evaluated directly on it, leaving it unclear which to select. We address this by evaluating the complete UDA pipeline, considering both adaptation and label-free selection together. Our study covers eleven clinically relevant cross-domain scenarios from nine medical imaging datasets, with ten UDA algorithms and 13 label-free selection methods (validators), evaluating over 80,000 trained models in total. By this, we find that a capable adapted model usually exists, but identifying it without target labels is difficult: the validator-selected models leave a large and structural target performance gap to the best available one, with no evaluated validator consistently reliable. Towards closing it, we explore two strategies, ensembling and a small target-labeling budget; both narrow this gap but do not close it entirely. Overall, deployable UDA depends on the complete pipeline; addressing the less explored selection step could bring much of current UDA closer to clinical use. --- ### LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration Authors: Enhuai Liu, Yunke Wang, Yutong Wang, Changming Sun, Chang Xu Published: 2026-08-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.12032v1 Video diffusion transformers are costly to sample: every denoising step applies self-attention over a long 3D token sequence, a quadratic cost that dominates as resolution and duration grow. Sparse attention reduces this cost without retraining, but existing methods pursue aggressive sparsity, where further speedup costs disproportionately more attention fidelity. We target the opposite end of this trade-off: fix near-lossless fidelity by construction, and remove as much computation as this constraint permits. Two observations make this regime practical: roughly 40% of block interactions can be removed while retaining 99% of the attention mass, and the high-mass support remains stable across denoising steps. We propose LoSA, a training-free sparse-attention method that fixes a retained-mass threshold of 99% rather than a sparsity ratio: it measures exact block attention masses at one early dense step, keeps, for each head and query block, the smallest key/value block set meeting the threshold, and reuses the frozen block indices for all remaining steps. On Wan2.1-1.3B, LoSA alone gives a $1.36\times$ speedup with a 0.06-point VBench Overall drop. The benefit is largest under composition: combined with feature caching, LoSA reaches a $3.2\times$ speedup on HunyuanVideo at a 0.02-point drop, versus 0.32 points for the strongest sparse baseline at comparable speed. Across three video diffusion transformers and speedups up to $3.2\times$, LoSA consistently achieves the best training-free speed-quality trade-off. --- ### Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision Authors: Shaojie Zhang, Ke Chen Published: 2026-08-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.12027v1 Pairwise constrained clustering typically relies on hard must-link/cannot-link labels, whereas realistic pairwise supervision may be real-valued and entangle intrinsic ambiguity, expert judgment, and stochastic corruption. Existing deep constrained clustering (DCC) methods mainly target hard, expert-agnostic constraints, treating soft labels mostly numerically rather than semantically. We formalize this setting as uncertainty-aware probabilistic constrained clustering (UPCC), defining a canonical aleatoric target through a heterogeneous observation process and analyzing its conditional identifiability. We introduce ProbPair, an angular pairwise objective for probabilistic relations, and build ECI-PP, an estimator--corrector--integrator framework that refines imperfect supervision via belief estimation, correction, and reliability-aware integration. Across challenging probabilistic supervision settings, experiments on diverse benchmarks show that ECI-PP outperforms state-of-the-art DCC methods and remains robust with a shared default configuration. --- ### SoftWater: Class-Aware Rate Allocation for Softmax Quantization Authors: Joao V. Cavalcanti, Ashia C. Wilson Published: 2026-08-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.12026v1 Post-training quantization pipelines routinely leave the softmax output layer in high precision. Yet in small LLMs with modern vocabularies, the head holds 15--30\% of all parameters, so a nominal ``2-bit'' model with an fp16 head can store several times as many bits per weight. We pose softmax-layer quantization as a rate-distortion problem under the KL divergence between the original and quantized output distributions. A second-order analysis reveals a class-aware geometry: quantization error is weighted jointly by feature covariance and class-specific softmax curvature. A separability approximation replaces the $Kn\times Kn$ Cholesky with one $n\times n$ factorization rescaled per class, making the lattice encodable by successive interference cancellation, with both statistics from a single forward pass. The resulting method, SoftWater, gives fine grids to frequent, low-variance classes and coarse grids to rare ones, a large gap under Zipfian token distributions. Across five models from 1B to 32B, SoftWater outperforms the released WaterSIC quantizer (near-optimal under linear-layer WMSE but not output KL) at matched head rates on 59 of 60 test points, using none of that pipeline's refinements and cutting head-induced KL by $6.5\times$--$8.3\times$ at 2 bits. On Llama-3.2-1B-Instruct with quantized bodies, a 2-bit head removes 45--60\% of stored bytes for a $2.9$--$3.7\%$ perplexity increase. Because the class-side statistic comes from calibration data, matching calibration to the deployment domain gives the lowest KL on that domain throughout. On a tied model, a 4-bit head is near-lossless and a 2-bit head costs under 4\% perplexity, making head quantization of such models practical. --- ### From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices Authors: Tuhinangshu Gangopadhyay, Rasmus Adler, Peter Liggesmeyer, Jan Reich Published: 2026-08-12 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.12025v1 Medical devices are becoming more software-intensive, connected, and AI-enabled. Their development requires risk-management evidence aligned with ISO 14971 and, for software, IEC 62304. This evidence must be kept consistent across requirements, design decisions, software changes, verification results, complaints, and post-market data. These tasks are costly and depend on scarce safety and domain experts. Large language models (LLMs) may reduce parts of this effort because medical-device safety work is highly document-based. However, current LLM-based safety-engineering studies often address isolated methods, rely on generic prompting or public examples, and provide limited support for source links, traceability, uncertainty handling, lifecycle updates, and recorded expert review. This limits their use in regulated medical-device development. This paper argues that the central research problem is not safety-text generation, but source-linked safety-knowledge support. We propose an evidence-grounded framework that connects device artifacts, controlled knowledge storage and retrieval, method-specific generation of candidate safety items, critique and uncertainty checks, and recorded expert review. The framework prepares, links, checks, and updates candidate safety artifacts for expert decision-making. It does not decide whether a device is safe and does not provide regulatory approval. We also outline an evaluation strategy using non-public or newly built medical-device case studies and expert reference analyses to assess coverage, correctness, relevance, traceability, duplicate rate, unsupported claims, and review effort. ---