# Research Papers — 2026-08 · bundle page 217 of 240 > Full-text markdown of papers #10801–10850 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/217 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/216.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/218.md) ### Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework Authors: Junwen Qiu, Bohao Ma, Andre Milzarek, Junyu Zhang Published: 2026-08-04 Categories: math.OC, cs.LG, math.DS, stat.ML arXiv: https://arxiv.org/abs/2608.03001v2 Unit excitation (UE) is a common assumption in stochastic saddle avoidance: the stochastic error must have a uniformly positive component along every direction, in expectation. This condition gives a direct way to rule out convergence to strict saddles, but it also oversimplifies the actual noise structure, and does not match many stochastic optimization regimes. In overparameterized or interpolation models, the noise may vanish near stationarity. In finite-sum problems, the stochastic gradient noise may lie in a low-dimensional, data-dependent subspace. In these (common) scenarios, UE is naturally not satisfied. In this paper, we prove an abstract almost sure avoidance theorem for stochastic recursions without UE. The theorem replaces UE-type requirements by verifiable pathwise conditions. In applications, these conditions follow, e.g., from local smoothness and finite-moment assumptions under standard i.i.d. sampling, or from the finite-sum structure under without-replacement sampling. Since the stochastically sampled maps generally do not share a fixed point, the celebrated center-stable manifold argument used in deterministic analyses is not directly applicable. Instead, we use a path-dependent change of variables together with a pathwise Lyapunov--Perron-based proof strategy. As applications, we obtain strict saddle avoidance for stochastic mirror descent (including SGD) and for random reshuffling. For nonsmooth composite objectives, we prove avoidance results for a proximal-type stochastic gradient method. Combining these insights with suitable iterate convergence guarantees, this allows establishing convergence to local minimizers of the original objective function. --- ### On the Non-Specificity of Statistical Measures Used in Script Decipherment Authors: Nikhil Raghavendra Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02999v1 Statistical regularities are routinely offered as evidence that undeciphered sign systems encode language; the Indus script debate is the canonical example. Any such inference rests on specificity: the reported outcome must be unusual among plausible structured non-languages. We test that premise constructively with SIGIL, a purpose-built generative emblem system whose 3,000-text core corpus carries explicit compositional meanings although no sign has a phonological value. A literature registry compiled in advance of evaluation records 54 methods and admits a method to exact scoring when both the published Indus outcome and a source-defined decision rule can be reproduced. SIGIL receives the same category as the Indus corpus on every criterion scored this way, across repetition, directional-asymmetry, and lexical-distribution tests. Declared reconstructions of entropy, frequency, positional, predictive, classifier, and network measures reproduce the familiar Indus-like signatures as well. A sequential decipherment stress test then reaches high dictionary coverage for English, Sanskrit, and Tamil on the same corpus, while grouped held-out declines and unstable keys reveal how little that coverage identifies. The construction does not decide what the Indus signs encode: it shows that the evaluated measures detect organization without being specific to language, and therefore cannot, on their own, establish encoded speech. --- ### On the missing benchmarks layer and a potential solution Authors: Francis F Daniel, Mauro Ibañez, Francis Perelman, Marian Basti Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.02996v1 Latin America is missing a foundational layer for native AI development: the benchmark layer. The benchmark layer does two things no other layer can - it audits AI systems against regional social requirements and it directs AI optimization in economically relevant environments. Without it, public institutions cannot independently evaluate foreign AI systems, and companies cannot optimize AI systems to solve local problems with SOTA performance. The cost of the missing layer is dual: a loss of auditability and a loss of optimization direction over a technology that is increasingly critical infrastructure. We propose an EvalsHub, with LatamBoard as its first regional instance - an open, task-first benchmark infrastructure where universities, public institutions, professional communities, and companies can publish, execute, compare, and maintain evaluations across models, workflows, and agents. Built once, measured forever - re-run by institutions as new AI systems ship and by industry teams after every system change. Open by design and incentive-driven by construction. --- ### SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels Authors: Yongwan Jo, Jinyoung Park, Euihyun Lee, Dokyung Song Published: 2026-08-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.02995v1 Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens. Researchers have leveraged this property to optimize LLM serving systems by omitting weight accesses and computations pertaining to inactive neurons. Unfortunately, however, such optimizations create input-dependent weight accesses, which can be leaked over side channels. We present SparSEEty, a new token extraction attack that exploits input-dependent neuron weight accesses introduced by sparsity-exploiting LLM serving systems. SparSEEty first constructs a neuron-activation oracle using neuron weight access side channels during LLM inference, and then inverts the activation traces to reconstruct the input tokens, forming an end-to-end token extraction attack. We instantiate SparSEEty against an LLM serving system protected inside an Intel TDX confidential virtual machine (CVM), addressing three key challenges: (i) constructing a neuron-activation oracle using a combination of side channels exposed by CVMs, (ii) reducing inference-time overheads of neuron activation monitoring for covertness, and (iii) accurately inverting partial binary activation traces back to tokens. Our evaluation shows that SparSEEty can reconstruct both prompt and response tokens with consistently high BLEU scores (>0.95) across various models and datasets, while incurring monitoring overheads of 3.7% to 7.2%. --- ### Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning Authors: Subrat Prasad Panda, Blaise Genest, Arvind Easwaran Published: 2026-08-04 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.02993v2 (Flat) Reinforcement Learning (RL) agents face significant challenges in environments with sparse rewards that require long-horizon reasoning. A compelling approach to improve sample efficiency is to incorporate knowledge into learning and decision-making. In standard Hierarchical RL (HRL), knowledge is encoded in a fixed, non-updatable form, such as architectural choices, and remains unchanged throughout learning. With fixed HRL, reasoning with incremental knowledge learned during exploration is impractical before sufficient environmental knowledge is acquired, leading to poor sample efficiency. In this work, we propose neurosymbolic HRL with {\em Incremental Knowledge (InK)}: symbolic high-level components perform {\em symbolic planning} (e.g. using $D^*$) on an updatable representation of current InK, while low-level goal-conditioned neural modules learn motion primitives through experience using reward shaping. Experiments on navigation tasks demonstrate that incorporating InK substantially improves sample efficiency. Additionally, to perform {\em optimal} symbolic planning given {\em prior} knowledge about the world, we develop Belief World Tree Search. The code is available at https://github.com/CPS-research-group/ink_bwts. --- ### Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learning Authors: Subrat Prasad Panda, Blaise Genest, Arvind Easwaran Published: 2026-08-04 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.02993v1 (Flat) Reinforcement Learning (RL) agents face significant challenges in environments with sparse rewards that require long-horizon reasoning. A compelling approach to improve sample efficiency is to incorporate knowledge into learning and decision-making. In standard Hierarchical RL (HRL), knowledge is encoded in a fixed, non-updatable form, such as architectural choices, and remains unchanged throughout learning. With fixed HRL, reasoning with incremental knowledge learned during exploration is impractical before sufficient environmental knowledge is acquired, leading to poor sample efficiency. In this work, we propose neurosymbolic HRL with {\em Incremental Knowledge (InK)}: symbolic high-level components perform {\em symbolic planning} (e.g. using $D^*$) on an updatable representation of current InK, while low-level goal-conditioned neural modules learn motion primitives through experience using reward shaping. Experiments on navigation tasks demonstrate that incorporating InK substantially improves sample efficiency. Additionally, to perform {\em optimal} symbolic planning given {\em prior} knowledge about the world, we develop Belief World Tree Search. The code is available at https://github.com/CPS-research-group/ink_bwts. --- ### Control Allocation in Neural Network Optimization: Joint Affine Control of Weight and Bias Updates Authors: Zhang Gongyue, Sheng Yixuan, Wang Zhiyong, Liu Donghan, Ren Weihong, Liu Honghai Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.02991v2 Optimization algorithms determine not only the magnitude of a neural-network update but also how that update is distributed across parameter channels. We study whether this distribution can be treated as a controllable quantity independently of global training progress. We define operational update allocation through normalized channel energies and analyze two scalar controls: a coordinate-preconditioning exponent and an affine spectral exponent that scales the bias column of an augmented weight--bias matrix. At a frozen state, a common nonzero step-size multiplier leaves normalized allocation unchanged; the coordinate exponent yields affine pairwise log-odds with an explicit inverse; and the affine exponent induces a rank-one positive-semidefinite Gram perturbation and a logistic raw-participation law. We further separate raw affine participation, spectral gain, and the decoded physical bias update, and show that finite polynomial spectral iterations preserve singular subspaces. Same-state replay verifies the exact control laws. On a five-seed controlled benchmark, intermediate controls improve held-out and worst-group metrics, whereas excessive affine control causes underfitting. A four-task single-seed transfer study provides descriptive corroboration. These results establish instantaneous allocation control and a bounded empirical operating regime, but do not imply a task-independent generalization ordering. --- ### Joint Affine Spectral Shaping: Coupling Weight and Bias Updates Beyond Weight-Only Muon Authors: Gongyue Zhang, Honghai Liu Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.02991v1 Matrix spectral optimizers reshape weight-update spectra but usually delegate vector-valued biases to a separate optimizer. We study whether this separation is neutral. We formulate each affine layer as a joint momentum matrix $A=(M_W,αm_b)$ and apply a capped regularized-inverse spectral map to the complete matrix, producing both the weight and physical bias updates. A strict five-seed ablation on a four-layer BERT-mini trained from scratch on IMDb compares exact-SVD Muon, weight-only inverse shaping, affine-probe inverse shaping, and the proposed joint regularized inverse (JRI). Weight-only inverse shaping raises validation-loss-selected test accuracy from $84.903\pm0.242\%$ to $85.562\pm0.308\%$ and lowers selected test loss from $0.3479$ to $0.3345$. Allowing bias to alter the joint SVD while retaining an independent Adam bias update does not improve over weight-only inverse shaping. Using the transformed bias jointly raises selected test accuracy to $85.738\pm0.180\%$ and lowers test loss to $0.3291$, with all five seeds improving relative to the probe baseline. During the peak-performance window, JRI preserves the eligible weight-update norm while reducing the bias-update norm from $0.02095$ to $0.00301$, lowers boundary-function share from $86.58\%$ to $78.97\%$, and changes the cosine between weight-induced boundary motion and explicit bias from $+0.030$ to $-0.137$. An independent 22-seed replication yields $85.743\pm0.203\%$ selected test accuracy. These results identify joint affine spectral allocation as a small but consistent extension to weight-only spectral optimization. --- ### AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding Authors: Shuang Liang, Hao Mark Chen, Zhiwen Mo, Qianzhou Wang, Guoyu Li, Lingxiao Ma, Wayne Luk Published: 2026-08-04 Categories: cs.LG, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2608.02989v1 Speculative decoding verifies a tree of draft tokens in one target-model forward pass. For a mixture-of-experts (MoE) target, however, parallel verification can activate the union of the experts selected by all tree nodes, even though only a small subset of those nodes reaches the accepted output. Token count, activated-expert union size, and expert-weight traffic are therefore distinct cost measures: reducing the token workload need not shrink the expert union proportionally, and under offloading, transfer traffic also depends on cache residency. We introduce AcceptMoE, a verifier-side expert selector that combines target-router scores with offline-estimated commitment probabilities and automatically adjusts the number of eligible experts for each verification block, eliminating the need for a user-specified expert budget. Under offloading, AcceptMoE conditions expert eligibility on cache residency instead of predicting natural routes and prefetching the corresponding expert weights. Although constraining target-expert eligibility changes the model distribution, across 12 model-task pairs spanning three MoE targets and four benchmarks, AcceptMoE's mean accuracy is 0.27 percentage points lower than that of EAGLE-3 speculative decoding with natural routing. Served with SGLang at batch size one, it reaches 1.290 times the throughput of this baseline with all expert weights in GPU memory, and 2.06 times under physical expert offloading, while reducing host-to-device traffic by 73.6 percent to 77.1 percent. --- ### Internalising the Identity Primitive: Cryptographic Individuality for an Autonomous Agent on a Public Blockchain Authors: Keisuke Suzuki Published: 2026-08-04 Categories: cs.CR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.02986v1 A software agent on a public blockchain accumulates authority and economic stakes, raising the engineering question of what makes it count as an individual. The paper's central contribution is a shift of trust root for the key-to-weights binding of agent identity: from hardware, operator, or wrapper trust to cryptographic assumptions enforced by a pinned implementation (liveness, key custody, oracle trust, and the underlying software stack remain external). We design and deploy on Solana devnet an agent whose neural-network weights are a deterministic function of its private key. The binding is committed in zero knowledge at genesis, re-checked against that commitment at every state transition, and signed by the agent into an on-chain history unforkable once finalized; in a PoC-tier extension, a protocol-imposed metabolic cost is debited each cycle from a key-derived economic account, adding a consumption-side economic-viability constraint to the key-history-economy triple. Empirically, the agent completes a 2.36-day on-chain run with two host-side resumptions but no rejected transition, at bounded per-transition verification cost; a substituted substrate is rejected on chain, and independently keyed agents diverge as predicted while a same-key control stays at zero. To our knowledge, this is the first published on-chain agent whose identity primitive is itself a cryptographic invariant re-checked at every state transition. The resulting transition-time invariant instantiates the cryptographic individuality proposed by Suzuki 2026's Artificial Externality framework. --- ### Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores Authors: Zeyu Zhang, Bradly C. Stadie Published: 2026-08-04 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2608.02985v1 The standard check for contamination in LLM backtests is simple: compare scores before and after the training cutoff. We show this check is uninformative. Four flagship models fail it on questions they cannot have memorized: every scored question resolved after their cutoffs. The reason is structural. Models legitimately know more about times near their cutoff, so recency mimics leakage, and we prove no passive backtest can separate the two from genuine skill. Measurement, not just detection, requires information from outside the backtest. We supply it in two forms. A known cutoff identifies leakage at the boundary; a matched clean control identifies it globally and yields a leakage-adjusted score. We also derive where leakage hides: it concentrates on outcomes that surprised the crowd and were well covered in training, and partial memorization is disproportionately rewarded. We validate the estimators against ground truth by planting leakage in twin models, where they recover the injected dose and return null on clean questions. Deployed on frontier models, they detect one cutoff-localized signature and, at the audit's power floor, clear five models whose apparent advantages were recency alone. Backtests need not be discarded; they need one defensible reference. --- ### Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding Authors: Lucy Lin, Ayush Jain, Yifan Liu, Katerina Fragkiadaki Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02980v1 Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to frame-centric tokenization and limited context windows. 3D geometry provides a natural compression mechanism for visual streams: depth and camera pose enable observations from multiple views and time steps to be fused into a persistent, world-aligned representation. While recent 3D LMMs leverage geometry-aware representations to improve spatial reasoning, they continue to lag behind specialist 3D perception systems on grounding and segmentation tasks. We argue that a key limitation is geometry-aware decoding: existing methods communicate 3D predictions through language tokens, proposal selection, or lightweight grounding queries, creating a bottleneck between language reasoning and dense geometric prediction. Building on these insights, we introduce Qwen-3D, a geometry-aware LMM that compresses visual information within the Qwen backbone using multi-view geometric cues, enabling efficient long-horizon visual reasoning over static scenes. Qwen-3D augments visual tokens with 3D Rotary Positional Embeddings, allowing attention to operate directly in 3D scene space rather than across independent image frames and thereby facilitating scalable cross-view and temporal reasoning. To bridge language and geometry, Qwen-3D incorporates a query-based segmentation decoder that grounds language directly in the underlying 3D scene representation, unifying referential grounding, instance segmentation, and visual question answering across both images and videos. Across a diverse set of benchmarks, Qwen-3D surpasses existing 3D LMMs and outperforms several large proprietary 2D models. Notably, Qwen-3D achieves these improvements while maintaining strong performance on standard 2D vision-language benchmarks by jointly training on 2D and 3D data. --- ### TQLite: Multi-LLM Jury Guided Distillation for Real-time MQM Translation Quality Evaluation Authors: Bhavin Jawade, Cameron R. Wolfe Published: 2026-08-04 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.02975v1 Large language models (LLMs) have demonstrated impressive performance in MQM-based translation quality (TQ) evaluation, and recent advances in large reasoning models (LRMs) promise even greater improvements. However, both LLMs and LRMs are computationally expensive to deploy at scale, while small language models (SLMs)---though much more efficient---struggle with the complex reasoning required for evaluation tasks. In this work, we present an extensive empirical study benchmarking SLMs, LLMs, and LRMs across a wide range of TQ evaluation setups, providing a comprehensive view of the current landscape and establishing best practices. To address the scalability challenge, we introduce TQLite, a novel distillation framework that enables SLMs to approach the MQM evaluation performance of the best LRM-based evaluators. Our approach leverages a multi-LRM jury to generate high-quality synthetic training data via practical data curation techniques and aggregation of evaluation responses across a diverse panel of models. Our results demonstrate that SLMs trained via TQLite achieve strong MQM evaluation performance that far exceeds off-the-shelf evaluation capabilities of standard SLMs, offering a scalable and cost-effective alternative to LLM- and LRM-based evaluators. --- ### Mapping the City Through the Lens of Language Models Authors: Wanqi Liu, Rong Zhao, Zhizhou Sha, Qinyu Cui, Yecheng Zhang Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02971v2 Language models often complete an underspecified reference to a city with unstated assumptions about urban size, form, infrastructure, environment, and function. We measure those assumptions without naming places. Ten open-weight checkpoints rate anonymized profiles derived from real morphological urban centres across 40 audited indicators and seven domains. The design combines constrained probability-based ratings, prespecified reliability screens, lineage-aware aggregation, multiple population weightings, an independent replication sample, and whole-profile validation. The clearest shared tendency favours urban profiles with larger developed area, faster recent growth, greater mapped infrastructure and non-residential capacity, and less sparse form. Most eligible directions recur in the replication data, and direct ratings of complete profiles show moderate agreement with the indicator-wise construction. Geographic differences shrink after accounting for city scale and development, while reliably measured paired tasks indicate that typicality and desirability are often closely aligned. The framework makes an otherwise vague notion of what models regard as an ordinary city empirically traceable. The resulting evidence delineates a shared yet model-dependent portrait of the city through the lens of language models. --- ### Mapping the City Through the Lens of Language Models Authors: Wanqi Liu, Rong Zhao, Zhizhou Sha, Qinyu Cui, Yecheng Zhang Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02971v1 Language models often complete an underspecified reference to a city with unstated assumptions about urban size, form, infrastructure, environment, and function. We measure those assumptions without naming places. Ten open-weight checkpoints rate anonymized profiles derived from real morphological urban centres across 40 audited indicators and seven domains. The design combines constrained probability-based ratings, prespecified reliability screens, lineage-aware aggregation, multiple population weightings, an independent replication sample, and whole-profile validation. The clearest shared tendency favours urban profiles with larger developed area, faster recent growth, greater mapped infrastructure and non-residential capacity, and less sparse form. Most eligible directions recur in the replication data, and direct ratings of complete profiles show moderate agreement with the indicator-wise construction. Geographic differences shrink after accounting for city scale and development, while reliably measured paired tasks indicate that typicality and desirability are often closely aligned. The framework makes an otherwise vague notion of what models regard as an ordinary city empirically traceable. The resulting evidence delineates a shared yet model-dependent portrait of the city through the lens of language models. --- ### HyperFL: Query-Adaptive Representation Learning for Software Fault Localization Authors: Shuai Shao, Yiming Zeng, Yu Zhao, Tingting Yu Published: 2026-08-04 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.02967v1 Software fault localization identifies the code locations responsible for reported issues and is a fundamental step toward automated debugging and program repair. Recent retrieval-based approaches formulate fault localization as a dense retrieval task by learning a shared embedding space between issue reports and source code. However, these methods encode all issue reports using a fixed query representation, despite the substantial diversity of real-world issue reports in length, structure, and debugging information. To address this limitation, we propose HyperFL, a query-adaptive representation learning framework for software fault localization. HyperFL employs a lightweight hypernetwork to generate query-specific LoRA parameters for the query encoder, enabling dynamic query adaptation while keeping the code encoder fixed and reusable. Experiments on a real-world issue localization benchmark demonstrate that HyperFL consistently improves retrieval performance across multiple embedding backbones, achieving up to 13.3% relative improvement in function-level MRR@10 and 16.7% relative improvement in Hit@1 over the state-of-the-art method SweRank. Further analysis shows that HyperFL learns distinct adaptation patterns for different issue characteristics, highlighting the effectiveness of query-adaptive representations for software issue localization. --- ### Large Language Models Exhibit Human-Like Bayesian Hypocrisy Authors: Nykko Vitali, Mahzarin R. Banaji Published: 2026-08-03 Categories: cs.HC, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.35779v1 Given recent achievements of large language models (LLMs), frontier models are expected to perform well on Bayesian reasoning tasks, at least as well as humans. Furthermore, there is no reason to expect that LLMs will condemn others who offer those very same Bayesian judgments, a fallibility observed in human decision-making (Cao, et al., 2019). In 5 experiments with 48 experimental conditions employing over 5,000 trials, GPT-4o and Claude 3.7 Sonnet were tested on two variations of a Bayesian reasoning task. We also assessed LLM evaluation of the competence and morality of a hypothetical person who had offered the same reasoning task as them. LLMs hovered near human performance on the Bayesian task, though their reasoning was more rule-based and rigid. Surprisingly, like humans but to a greater extent, LLMs also demonstrated the same hypocrisy in condemning others who, like them, had deployed Bayes' rule. In demonstrating Bayesian hypocrisy, LLMs highlight a humanlike error of a dissociation between self-performance and other-judgment, and caution against their use in domains where statistical fidelity and fairness norms collide. --- ### ToW3D: Consistency-aware Interactive Point-based Mesh Editing on GANs Authors: Haixu Song, Fangfu Liu, Chenyu Zhang, Yueqi Duan Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.26078v1 In this paper, we propose ToW3D that enables precise and consistent control over 3D generative adversarial networks (GANs) with the Tug-of-War competition between shape deformation and appearance consistency. Existing point-based GAN editing methods such as DragGAN and GANWarping have yielded impressive performance for 2D image manipulation. However, as 3D generators present weaker generalization ability compared with 2D due to limited training data, they would suffer from drastic changes in global appearance when editing local areas of meshes. To address this, we design a pipeline of ``drag locally, shove globally'', which iteratively performs two optimization steps: 1) pull the point towards the target, and 2) push the structure and semantics back to the source. Specifically, we design a structure adaption module based on structure which guarantees the preservation of basic geometric properties, and a semantic preservation module that maintains semantic similarity across different views. Extensive qualitative and quantitative experiments demonstrate superiority of our ToW3D approach over prior methods in terms of appearance consistency and fidelity especially under large deformations. --- ### Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization Authors: Yoshiyuki Ootani Published: 2026-08-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.20166v2 Tiny transformers trained on fully-enumerable tasks occupy an unusual position in the study of grokking: every input can be evaluated, every generalization ceiling can be computed exactly, and hundreds of seeds cost minutes. We argue this regime is a scientific instrument with four capabilities that approximate settings cannot offer: (a) exact, falsifiable generalization ceilings; (b) task surgery that manipulates one structural variable while provably fixing all others; (c) direct observation of every weight; and (d) survival-time statistics over many seeds that recast "does not grok" as a censored observation. The obvious objection is that laws characterized at 10^4 parameters may not mean anything beyond them. We answer it with a preregistered conservation study: three task-side laws established at 12K parameters -- a recoverability-ceiling law, a role-conflict delay law, and a weight-decay response law -- are re-measured under an identical from-scratch protocol at 12K, 1M, and 50M parameters (a 4,000x span; 360 runs plus a 44-run control arm). The ceiling law and the delay law are conserved (0/144 Holm-corrected ceiling violations; Spearman rho >= 0.75 at every scale, permutation p < 1e-4), while the weight-decay law deforms systematically, steepening with scale. Preregistered controls show the 50M role-conflict deficit survives learning-rate adjustment and a tripled budget. Conservation was tested against criteria frozen before data collection, and the third relationship fails that test even at the original scale, which is what tells us the test could have failed. The series scales the model while the tasks stay enumerable, so what it licenses is specific: the quantities this regime computes from a task keep predicting once the model has outgrown the regime itself. --- ### Domain-Adaptive ASR for Telephony AI Agents: Fine-tuning Canary Flash Models for Enterprise Contact Center Applications Authors: Chanameth Boonpramuk, Winn Voravuthikunchai, Songpol Bunyang Published: 2026-08-03 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2608.24916v1 This technical report describes Botnoi Group's methodology and results for rapidly fine-tuning the open-source NVIDIA Canary 180M Flash and NVIDIA Canary 1B Flash multitask models for speech-to-text tasks using the NVIDIA NeMo framework, with a focus on telephony-grade audio. To support this adaptation, we construct a telephony-oriented fine-tuning dataset from live voicebot system recordings and prompted speech with telephony-oriented augmentation. We evaluate four targeted experiments-language adaptation (Thai), telephony robustness, domain-specific jargon (names and addresses), and latency-using character error rate (CER) for accuracy and real-time factor (RTFx) for inference speed. Results show that fine-tuning substantially improves recognition in noisy telephony environments, reducing CER from 23.31% to 9.04% on BOTNOI telephony data, and further improves business-critical names and addresses from 16.98% to 3.78% CER through domain-specific adaptation. Overall, our results show that domain-adaptive fine-tuning enhances business-critical terminology while preserving real-time responsiveness for production voicebot deployments. --- ### ODG-NoMaD: Overhead-Camera Direction-Guided NoMaD Authors: Blossom Treesa Bastian, Keerthi S. Shetty, Manish Kolachalam, Rani Malhotra, Ashish Dutta Published: 2026-08-03 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.21395v1 NoMaD (31) is a learned vision-navigation policy that unifies goal-conditioned navigation and exploration in a single goal-masked diffusion policy. In an unseen environment, however - where neither a goal image nor a topological map is available - it can only explore undirectedly, wandering without global awareness. We present ODG-NoMaD, which gives NoMaD's exploration mode a global sense of where to proceed, without retraining the policy. An overhead depth camera is used once on deployment to build an occupancy map and plan a global path, which is segmented to yield a desired heading; a per-frame traversability map from the robot's onboard depth then refines this into a collision-free direction. The gradient of a cosine direction cost is injected into the final denoising steps, rotating sampled trajectories toward this direction while preserving the multimodality of exploration. In simulated office environments with and without random obstacles, ODG-NoMaD reduces the residual distance to the target by up to an order of magnitude over unguided exploration, outperforms the point-goal cost guidance of NaviDiffusor (37), and is the only configuration that remains collision-free on every trial. --- ### When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models Authors: Sina Alemohammad, Denghui Zhang, Bolong Tang, Anthony Qin, Gengchen Mai, Ahmed Abbasi, Richard Baraniuk, Zhangyang Wang Published: 2026-08-03 Categories: cs.DL, cs.AI arXiv: https://arxiv.org/abs/2608.19230v1 As language models move from drafting prose to running literature-search agents with tool calls, fabricated references are becoming easier to catch and constrain. The harder failure begins after every candidate is real: different models may still select the same narrow subset, producing citation monoculture without any single citation being wrong. We isolate this effect on 120 real papers. Eleven models from three vendors choose at most ten papers from uniformly random panels of thirty, with real titles and abstracts but fabricated authors, reassigned years, and hidden venues and citation counts. Each run is compared with indifferent selection on the same panel and realized budget. All eleven models concentrate sharply: the top decile receives 23.3-30.2% of citations against 15.6% under the null, one component explains 68-73% of variation across their preference maps, and cross-vendor agreement nearly matches within-vendor agreement. Formalizing the task as fixed-budget subset selection, we turn these patterns into identifiable mechanisms: an exchangeability bound rejects a mapless selector for every model, a spectral decomposition explains why the best cross-fitted mixture still retains 55% of the excess, and a rarity theorem predicts the recursive competition effect we verify within panels. Controlled paraphrase, content-slot crossover, and design resampling attribute about 90% of GPT-5 mini's map variance to paper content. Eight domain experts selecting from the same blinded panels under the same cap show no comparable shared preference, while model concentration persists in selection-only mode. Even when every reference is real and every paper is equally visible, current language models impose a common content-level filter on scientific attention. Equalizing retrieval or mixing vendors is therefore insufficient; the shared preference map itself must be changed. --- ### Language Models for Portuguese: A Systematic Mapping Study Authors: Jhessica Silva, Carlos Caetano, Helena Maia, Breno Bernard Nicolau de França, Sandra Avila, Helio Pedrini Published: 2026-08-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.18138v2 In recent years, the rapid development of language models has transformed the field of Natural Language Processing through a wide range of applications. However, the development of language models has not progressed uniformly across all languages. In the case of the Portuguese language, there has recently been a growing effort by academia and companies to develop language models and create data resources for Portuguese. These efforts have resulted in the rise of an increasingly diverse ecosystem of language models for Portuguese. However, information on these models remains dispersed in scientific publications, technical reports, model repositories, and project documentation. This survey presents a systematic mapping study of language models developed for Portuguese, providing a comprehensive overview of the current state of the field. We map a total of 46 models, characterizing them by various aspects, including base model, architecture, computational resources, training datasets, licensing, code availability, data, and model weights. Furthermore, we analyzed the evolution and relationships among these models through a phylogenetic perspective, identified current research gaps and opportunities, and discussed future directions for the development of language models for Portuguese. --- ### MITRE-SAGE: A Multi-Agent Cybersecurity Question-Answering Model Authors: Ali Habibzadeh, Farid Feyzi, Reza Ebrahimi Atani Published: 2026-08-03 Categories: cs.IR, cs.CR, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2608.16921v3 Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly struggle with information overload, alert fatigue, and time-constrained decision-making. Although large language models (LLMs) have demonstrated promising capabilities for question answering (QA), their effectiveness in cybersecurity remains limited by insufficient domain knowledge, a tendency to hallucinate, and difficulties in capturing both semantic and structural relationships. This work proposes MITRE-SAGE, a multi-agent retrieval-augmented generation framework that integrates semantic and structural cybersecurity knowledge to improve the reliability and interpretability of LLM-based QA systems. By decomposing complex tasks into query interpretation, evidence retrieval, and answer synthesis, MITRE-SAGE effectively supports cybersecurity tasks such as vulnerability assessment, threat profiling, and relationship extraction. Furthermore, we propose MITRE-QA, a comprehensive benchmark comprising 3,000 question-answer pairs for evaluating LLMs across diverse cybersecurity knowledge tasks, and use it to systematically evaluate MITRE-SAGE against representative baseline methods. Extensive experiments demonstrate that MITRE-SAGE consistently outperforms standalone LLMs and conventional RAG approaches. Notably, a lightweight configuration comprising Qwen2.5-7B sub-agents and a Qwen2.5-14B orchestrator achieves superior performance on five of the eight benchmark tasks, indicating the effectiveness of the proposed multi-agent framework. The results highlight the potential of MITRE-SAGE as a scalable and interpretable approach for reliable cybersecurity QA, while MITRE-QA provides a standardized benchmark for future research. --- ### Take it Personally: The Limits of General SSL Representations for Real-Life PPG Emotion Detection Authors: Dominika Kunc, Przemysław Kazienko, Stanisław Saganowski Published: 2026-08-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.14675v1 While Self-Supervised Learning (SSL) effectively extracts general representations from noisy, unconstrained physiological signals such as photoplethysmography (PPG), its suitability for highly subjective tasks remains unproven. In this work, we evaluate the efficacy of PPG-based SSL for real-life intense emotion detection. First, we pretrain a Real-Life PPG encoder (RL-PPG) on unconstrained, real-life data. As a rigorous sanity check, we demonstrate that these representations transfer exceptionally well to an objective physical activity recognition task, yielding almost 5-fold increase in performance over baselines in a leave-one-subject-out evaluation (LOSO). However, when applied to a~subjective real-life emotion detection task, these same general representations fail to surpass naive baselines under the LOSO protocol. Using an Across-Time validation strategy, we establish that incorporating an individual's personal data during fine-tuning is the main driver of predictive performance, outweighing the benefits of population-level pretraining. Ultimately, our findings indicate that in the evaluated scenario, general SSL representations may be insufficient for subjective affective inference, suggesting that personalization is likely a key component for real-world emotion recognition. To support future research, we share the code and pretrained RL-PPG~encoder~weights. --- ### A Human Audit of OpenAIs AI-Generated Mathematical Proofs Authors: Mikołaj Sienicki, Krzysztof Sienicki Published: 2026-08-03 Categories: cs.AI, cs.GL, quant-ph arXiv: https://arxiv.org/abs/2608.14673v3 We assess 18 chapter-specific reviews of the ten mathematical results announced by OpenAI on 1 August 2026, alongside review standards, Lean formalizations, subsequent research, and mathematical references. The article audits this review record without claiming a complete reconstruction of all ten proofs. No confirmed substantive mathematical error in a principal result remains in the examined assessments, although review depth varies and some dependencies remain partly checked. Chapter 8 presents the strongest reservation: a specialist review requests major revision of compressed analytic arguments. In Chapter 6, an apparent polarity error was withdrawn after an overbar lost during PDF extraction was recovered from the typeset source. Subsequent research independently reuses the Chapter 3 proof mechanism and confirms that Connes's rigidity conjecture is false, without independently reproducing Chapter 4's stronger infinite-family result. Among the cited follow-ups, Chapter 7 receives the strongest direct theorem-level corroboration through a stronger hardness theorem. Related equality results in Chapter 8 do not verify the analytic inequality proof. Some follow-ups disclose material AI assistance. We argue that confidence should combine formal checking, human reconstruction, independent mathematical use, and a public record supporting correction of both proofs and reviews. --- ### Continual Evolution Strategies in Control Tasks Authors: Nicola Pitzalis, Eleni Nisioti, Antonio Carta, Davide Bacciu, Andrea Cossu Published: 2026-08-03 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2608.13600v1 We study Evolution Strategies (ES) for continual control, where agents must adapt to changing tasks without forgetting previous ones. On sequential MuJoCo locomotion tasks, naive ES suffers from severe catastrophic forgetting. Replay substantially improves retention and can induce positive transfer, while larger replay budgets reduce plasticity. Overall, these results show that ES can support continual adaptation in control and that replay is an effective mechanism for mitigating forgetting. --- ### EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents Authors: Yuxi Qian, Yuxiang Ren Published: 2026-08-03 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.11248v1 Long-term memory is essential for language agents operating across extended interactions and evolving tasks. Existing memory-augmented agents mainly focus on storing and retrieving past experience, but the quality of stored memories may degrade over time. In particular, previously distilled insights can become outdated, over-generalized, or harmful under new task contexts, causing memory pollution when repeatedly reused. To address this issue, we study insight-level memory maintenance for long-term language agents and propose a failure-aware memory maintenance framework based on an editable insight graph. Each insight node tracks positive evidence, negative evidence, and an activation state, enabling the agent to distinguish reusable insights from conflicting or invalid ones. We further introduce a utility-aware retrieval mechanism and a graph controller that updates the memory graph after task execution by keeping reliable insights, archiving invalid ones, revising outdated ones, and adding newly discovered reusable insights. Extensive experiments show that our method consistently outperforms representative memory-based agent baselines across different backbone models. Ablation studies further demonstrate that append-only memory is insufficient for long-horizon tasks, while evidence-aware retrieval and graph-level editing improve memory reliability and downstream task performance. --- ### Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier Authors: Zafar Hussain, Kristoffer Nielbo Published: 2026-08-03 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.11247v1 Recent advances in language models have enabled collaborative settings in which multiple models leverage one another's capabilities, iteratively improving, transforming, and extending each other's outputs. Each agent sees what the others assert before it answers, so peer opinion competes with the model's own parametric knowledge, and a wrong majority can overturn an answer the model would otherwise get right. We measure that displacement in 23 open-weight models, 19 conditions, and three datasets, yielding more than a million graded responses. A unanimous wrong majority reverses 22.8% of a model's correct MMLU answers, 54.8% on GPQA and 71.0% on SimpleQA, and 84-89% of the reversed answers match the peers' answers. Existing mitigations aim to increase Resistance, the rate at which a model keeps its correct answer under this pressure, which is only half of what a collaborating agent needs. We pair it with Receptivity, the rate at which a model adopts a correct peer answer after initially answering incorrectly. We score six methods on both axes, four drawn from prior work and two of our own. Each gains Resistance only by losing Receptivity, and their means fall on a single Resistance-Receptivity frontier with $R^2$ between 0.80 and 0.90. Reflection, the strongest published method, gains 7.9 points of MMLU Resistance and gives up 15.3 of Receptivity. Reasoning is the one exception. On GPQA and SimpleQA it trades like the rest, but on the MMLU subjects whose answers a model can derive for itself it raises Resistance by 7.2 points and Receptivity by 9.6 at once, the only intervention we find that improves both. --- ### Towards the Harness of Embodied Agents Authors: Qi Wang, Tianyi Wang, Chengyang Li, Shikun Ban, Yurun Chen, Yizhong Ge, Jason Qin, Chengtai Li, Wentao Zhu Published: 2026-08-03 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2608.11246v1 The success of coding agents has established the harness as a paradigm: what an agent achieves depends not on the model alone, but on the infrastructure around it. We ask whether the same paradigm extends to embodied agents in the physical world. We present Thea, a harness in which an agentic loop orchestrates robot capabilities, each wrapped as a callable tool. It inherits the core components of coding agents, modified as the physical world requires. The world, however, withholds two abilities that software grants for free: reading the state of the world, and judging the outcome of an action. To bridge these gaps, Thea introduces Scene Graph as Context, a persistent, symbolic representation of the world, and Evaluation as Exit Codes, which detects when an action should terminate, judges whether it succeeded, and on failure diagnoses the cause. Together they close the loop between the agent and the physical world. Rich behaviors then emerge from the composition of tools, and the closed loop carries long-horizon tasks to completion in real environments. --- ### Temporal Generalization in fNIRS-Based Autism Classification: A Cross-Time-Window Transfer Benchmark Authors: Marios Petrov, Sahana Vinayak, Targol Bakhtiarvand, Moses Smith Guddah, Adham Atyabi, Frederick Shic, Kevin A. Pelphrey Published: 2026-08-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.07567v1 Functional near-infrared spectroscopy (fNIRS) is a promising modality for autism spectrum disorder (ASD) classification, yet existing approaches assume temporally aligned evaluation. In practice, the optimal observation window varies across subjects due to differences in hemodynamic delay and neurovascular coupling, creating a temporal distribution shift that degrades performance. We formalize this as a \textit{cross-time-window transfer problem}, introducing a protocol that varies window length (2.5--10\,s) and offset within biological motion trials. Using topographic map representations of fNIRS recordings, we benchmark three vision architectures under two zero-shot baselines and eight adaptation strategies under leave-one-subject-out cross-validation ($N{=}124$). Key findings: (1) zero-shot cross-window accuracy is near chance (54--69\%); (2) ${\approx}5\%$ subject-specific fine-tuning recovers 90--96\%, while a subject-specific upper bound reaches 97--100\%, identifying inter-subject variability as the dominant barrier; (3) domain-adversarial and self-supervised strategies achieve 78--90\% without target-subject data; and (4) discriminative information is recoverable from windows as short as 2.5\,s. These findings provide a practical roadmap for deploying fNIRS-based ASD classifiers under realistic temporal variability. --- ### The Field Knows: Cross-Dimensional Geometry from Navigation to Black Holes Authors: Chenghao Xu Published: 2026-08-03 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.07566v1 We introduce a continuous metric field framework trained by a single causal contrastive loss. The framework encodes a scene into coefficients of a fixed symmetric matrix basis, assembles them into a Lie algebra element, and exponentiates the result to a Riemannian or Lorentzian metric. Across dimensions, this field discovers the full spectrum of geometric structures: from obstacle-avoiding geodesics in robot navigation across planar and manipulator configuration spaces, to event horizons of black holes in Lorentzian spacetime. Extensive zero-shot generalization studies demonstrate that the field captures transferable geometric structure rather than memorizing specific configurations. In the black hole setting, the causal loss spontaneously evolves genuine black-hole-like structures with the correct Lorentzian signature. The same loss, the same architecture, and the same training protocol produce the full range of geometric phenomena across dimensions. The field knows geometry, and geometry knows physics. --- ### What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems Authors: Zhijing Zhang, Jinpeng Yu, Xin Song, Bingnan Li, Chuyue Li, Changhui Du, Xiaolin Fang, Jiaming Liu, Ruihua Huang Published: 2026-08-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.07565v2 Conversational assistants increasingly recommend follow-up edits to help users continue a task. Existing systems primarily target text-only interactions, leaving image-creation conversations underexplored. In image-creation tasks, useful follow-up edit suggestions must reflect user preferences, offer diverse directions, and remain executable on the current image. We collected 100,000 real multi-turn image-creation conversation samples from Qwen App and found that 80.1% are image-dependent, underscoring the need for multimodal recommendation. We address this setting with a three-stage framework. In Stage 1, we use real online data to build a human-reviewed table of appropriate follow-up editing intents, then create SFT targets and fine-tune a multimodal policy. In Stage 2, to align rule-guided SFT suggestions with actual user choices, we use user click feedback to optimize the policy through multi-objective reinforcement learning. In Stage 3, to reduce visual inconsistencies between suggested edits and the current image, we introduce a visual verifier as additional training supervision. Extensive experiments demonstrate that our framework significantly outperforms baselines on both automatic and human evaluations. In a live user-randomized A/B test with millions of users, our final framework reduces visual inconsistency from 3.7% to 0.9%. Furthermore, it significantly improves recommendation CTR by 32.70%, image take-away rate by 16.32%, and average conversation turns per user by 39.90% (all p<0.05). Project page: https://what-to-edit-next.github.io/ --- ### Coarse-to-Fine Registration of Jawbone CT and Intraoral Scan Data Using GeDi and ICP with Pseudo-IOS Ground Truth Authors: Sho Mitarai, Hikaru Kayo, Hisashi Ozaki, Yuichiro Imai, Megumi Nakao Published: 2026-08-03 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.07564v1 In digital dentistry and oral surgery, the registration of jawbone CT and intraoral scanner (IOS) data is essential for integrating internal bone structure with high-resolution dental surface geometry. However, this registration is challenging because the two modalities share only a limited region in common, and their true correspondence is generally unknown. This uncertainty has prevented rigorous quantitative evaluation of registration accuracy. In this study, we propose a pseudoIOS evaluation framework in which a point cloud emulating an intraoral scan is generated from CT data within the same coordinate frame, so that the transformation between them is known by construction and can serve as a true ground truth. Using this framework, we propose a coarse-to-fine registration method that combines a domain-generalizable local descriptor (GeDi) for initialization-independent global alignment with the iterative closest point (ICP) algorithm for local refinement, and also evaluate the influence of metal artifacts on registration. In experiments on seven cases, ICP alone frequently converged to local minima from a perturbed initial position, whereas GeDi$+$ICP maintained submillimeter mean absolute error (MAE) across all evaluated jaw and artifact conditions (0.55-0.69 mm). A three-way repeated-measures analysis confirmed that GeDi$+$ICP was significantly more accurate than GeDi alone. Metal artifacts had a statistically detectable overall effect, but their absolute impact on GeDi$+$ICP was small. --- ### ADIAS: Automated Design of Interactive Agentic Systems Authors: Lekang Jiang, Bohan Tang, Stephan Goetz, Yiwen Guo Published: 2026-08-03 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2608.06410v1 Automated agent design improves agent harnesses through iterative revision, evaluation, and feedback summarization. Existing methods are largely candidate-centric: cross-round experience is organized around candidate agents, which leaves the repair progress implicit. This causes inefficient repair targeting, slow consolidation of partial progress, and propagation of ineffective interventions across rounds. Therefore, we formulate issue-centric agent optimization, in which repair progress is carried forward as an explicit persistent issue state to guide optimization, rather than re-derived from candidate history in each round. We instantiate the formulation in ADIAS, a framework for automated full-code agent design with two mechanisms. A persistent issue state maintains stable issue identities, lifecycle status, supporting evidence, and intervention-outcome histories. Issue-guided optimization uses this state to jointly propose repair targets and revision directions for subsequent focused full-code modification. Across five interactive benchmarks, ADIAS outperforms the strongest baseline by 25.2% on average and achieves consistent gains across four backbone models. Controlled ablations further show that removing persistent issue state or replacing issue-centric revision with candidate-centric policies leads to performance drops of up to 40.7%. --- ### Separating Decision-Rule Misalignment from Readout-Coverage Limitations in Speech Language Models Authors: Linkai Peng, Baorian Nuchged Published: 2026-08-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.06409v1 Speech language models are increasingly evaluated on paralinguistic tasks by the accuracy of prompted answers, but answer accuracy combines failures at different stages of the audio-to-answer computation. We introduce a generation-aligned diagnostic ladder that compares the emitted answer, the option logits, an affine readout of those logits, and a linear readout of the hidden state at the same answer token. Successive differences separate endpoint, decision-rule, and readout-coverage gaps. Across five systems and two emotion corpora, state decoding exceeds generation by 27.8 accuracy points on average, and both the decision-rule and readout-coverage gaps are positive in all ten conditions. A label-free logit correction improves generated accuracy in every condition, showing that part of the decision-rule gap is actionable. In rank-matched comparisons, emotion information outside the native readout generalizes to held-out speakers and survives controls for measured acoustic descriptors, but replacing the selected readout-external directions usually has little effect on emitted answers. These results distinguish information availability from behavioral use and localize performance losses across the decision rule and the state-to-answer readout. --- ### SubtleTalk: Generating Controllable Weakly-correlated Facial Dynamics for 3D Talking Heads via Residual Flow Matching Authors: Chenyang Ding, Shuai Tan, Qunfen Lin, Xinwei Jiang, Zijiao Zeng, Ye Pan Published: 2026-08-03 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2608.06408v1 Audio-driven 3D facial animation aims to synthesize realistic and temporally coherent motions from speech. Despite notable progress in lip synchronization, weakly correlated dynamics, including eyebrow movements, eye blinks, and head motion, which are essential to photorealistic facial animation, remain difficult to model faithfully and often appear static or unnaturally repetitive. We attribute this limitation to three factors: (a) insufficient conditioning for weakly correlated dynamics; (b) the limited ability of deterministic regression to capture diverse motion patterns; (c) data bottlenecks from unreliable upper-face pseudo-labels and limited dataset diversity. To address these issues, we propose SubtleTalk, a framework for generating natural and controllable weakly correlated facial dynamics via multi-condition modeling and residual flow matching. First, to compensate for the limited guidance of speech alone, we introduce interpretable controls, including prosody, regional intensity, and Valence-Arousal signals, to explicitly capture the timing, magnitude, and affective variation of weakly correlated dynamics. Second, to overcome the limited expressiveness of deterministic regression, we build residual flow matching based on a stable speech-driven motion prior, allowing the model to capture stochastic deviations beyond deterministic prediction. Third, to alleviate the data bottleneck, we construct SubtleTalk-Face, a large-scale 3D facial animation dataset comprising about 3,900 identities and 74 hours of data, built via a simple and scalable pseudo-labeling pipeline and featuring improved upper-face tracking and frame-level VA annotations. Extensive experiments demonstrate that our method significantly improves the realism and diversity of weakly correlated facial dynamics while preserving accurate lip synchronization. --- ### TransSLR: A Lightweight Transformer for Sign Language Recognition Authors: Lucia Yen Wanchi, Samuel Johnny, Victor Tolulope Olufemi, Emmanuel Aaron, Moise Busogi Published: 2026-08-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.06407v2 Automated sign language recognition for underrepresented languages remains a largely unsolved problem. Central African Sign Language (CASL) exemplifies this challenge: the CASL-W60 benchmark contains 60 isolated signs, and the best published result is 69.93%. We present TransSLR, a lightweight Temporal Transformer Encoder trained from scratch on normalized 64-frame pose sequences. By operating on geometric keypoint representations rather than raw RGB, TransSLR achieves 80.39% top-1 accuracy and 91.07% top-5 accuracy on a signer-independent evaluation split. This result is 10.46 percentage points higher than the published 69.93% result. TransSLR has 8.67 million trainable parameters. We also evaluate zero-shot transfer from a high-resource sign-language model, which achieves 0.00% exact-match accuracy under our manual gloss-matching protocol. Our experiments compare pose-based, RGB-based, and multimodal approaches to sign-language recognition for a low-resource language. --- ### Deep Evidential Regression for Sparse Forest Height Estimation from Multimodal Satellite Imagery Authors: Laura Bader, Muhammad Ammar Ahmed, Xiao Xiang Zhu, Göran Kauermann Published: 2026-08-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.06406v2 Accurate estimation of forest height from satellite imagery is essential for applications such as carbon accounting, biodiversity monitoring, and ecosystem management. While recent deep learning approaches provide accurate predictions, they typically do not quantify predictive uncertainty. This limitation is particularly relevant in geospatial settings characterized by sparse supervision and geographic distribution shift. In this work, we investigate Deep Evidential Regression (DER) for forest height estimation on the TreeUQ benchmark, a large-scale dataset designed for the joint estimation of tree count and average tree height at 10 m resolution, based on Sentinel-1/-2 data as well as tree inventory data over the federal state of Bavaria. To account for the extreme label sparsity of the tree inventory data, we introduce a masked evidential loss for dense geospatial prediction. Using a U-Net architecture with multimodal Sentinel-1 and Sentinel-2 inputs, the proposed approach jointly predicts tree height and associated uncertainty estimates in a single forward pass. Experimental results show that DER achieves predictive performance comparable to a deterministic U-Net while additionally providing well-calibrated uncertainty estimates. These findings demonstrate the potential of evidential learning as an efficient framework for uncertainty-aware forest structure estimation from Earth observation data. --- ### UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys Authors: Junxiong Zhou, Xuechen Li, Chonghao Qiu, Lang Qiao, Xiaowei Jia, Qi Yang, Chishan Zhang, Leikun Yin, Nanshan You, Vipin Kumar, David Mulla, Ce Yang et al. Published: 2026-08-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.06404v1 Accurate 3D crop monitoring underpins data-driven precision agriculture by enabling field-scale analysis of plant structure, growth dynamics, and management response. Modern 3D reconstruction methods perform strongly on generic benchmarks, but rendered appearance may not translate into metrically and agronomically useful geometry in crop fields. We introduce UAV3DCrop, a public benchmark of repeated multi-angle unmanned aerial vehicle (UAV) crop surveys. It contains 88,830 RGB images at $5280 \times 3956$ pixels, with a ground sampling distance of 3.6-5.8 mm, from 91 scenes spanning corn, soybean, wheat, and oat. Track A evaluates seven scene-optimized methods -- Neural Radiance Field (NeRF) and 3D Gaussian Splatting (3DGS) variants -- on held-out views, photogrammetry-referenced depth, and canopy-height recovery. Track B tests four pretrained feed-forward models on zero-shot camera-pose and geometry estimation. The scene-optimized methods rank differently across the three targets: Splatfacto-big leads appearance, whereas Scaffold-GS leads depth and is statistically tied with Splatfacto for canopy height. Among feed-forward models, MapAnything leads on seven of the eight metrics, while the remaining models vary more across crops and fail severely on absolute scale in a way that alignment conceals. Repeated acquisitions reveal further sensitivities that differ by output type and by model, associated with position within the acquisition sequence and with tie-point multiplicity. Current 3D reconstruction methods are therefore not yet interchangeable for agronomic use: no single method wins on appearance, geometry, and canopy height at once, and only one of four feed-forward models recovers usable metric scale. The dataset is publicly available at https://link-dev.github.io/UAV3DCrop/ --- ### CLARA: Clarification of Language Ambiguity through Result Analysis for Natural-Language Cancer Genomics Queries Authors: Pratyush Kumar Shukla, Manveer Singh Tib, Siddhant Garg Published: 2026-08-03 Categories: q-bio.GN, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2608.05195v1 A natural language interface can be used to make cancer genomics databases easier to use, but even if a question is perfectly fluent, its scientific meaning can be ambiguous. We propose CLARA, a framework that represents a question as a typed scientific query specification, considers a few possible interpretations, executes them, and asks for clarification when the estimates diverge. CLARA was assessed on mutation-prevalence contrasts among eight TCGA PanCancer Atlas cohorts and a 30-gene panel. This benchmark consisted of 330 unique executable contrasts varying in mutation scope, assay denominator, and sample context; 115 contrasts were result-sensitive and 215 were result-stable, per the preregistered definition of relative divergence greater than 0.10 or absolute divergence greater than 5 percentage points. An independently implemented pandas execution engine perfectly replicated all 660 results from the SQLite engine. In a separate 120-question LLM-generated, manually vetted language stress test, CLARA recognized all 60 result-sensitive contrasts and needlessly clarified 13 of 60 stable contrasts (accuracy 89.2%, sensitivity/recall 100%, specificity 78.3%). Standalone machine learning had superior overall accuracy (97.5%) but missed one critical contrast. This demonstrates that downstream execution can distinguish consequential from inconsequential ambiguity and reveal an explicit trade-off between safety and burden. --- ### Reconstructing Persistent Worlds from Narratives for Narrative-Grounded Interactive Experiences Authors: Yi-Chun Chen Published: 2026-08-03 Categories: cs.CL, cs.AI, cs.GR, cs.HC arXiv: https://arxiv.org/abs/2608.04037v1 Designing narrative-grounded interactive experiences remains labor-intensive because interactive content must align with the underlying world implied by the narrative. Existing approaches formulate problems such as narrative planning, scene generation, and gameplay generation, each constructing computational representations tailored to specific downstream tasks rather than explicitly reconstructing and maintaining the persistent world that grounds them. We investigate reconstructing explicit persistent worlds from narrative descriptions as the central computational objective for narrative-grounded interactive realization. Rather than treating the world as an implicit by-product of downstream generation, our approach reconstructs and maintains persistent entities, locations, semantic relationships, and evolving world states while inferring only the contextual information required to support coherent interactive experiences. To investigate this perspective, we develop a reference prototype that reconstructs structured persistent world representations from narrative descriptions and subsequently instantiates playable tile-based environments. Through three representative case studies spanning a procedural scenario, an original fantasy narrative, and an adapted public-domain story, we demonstrate the feasibility of reconstructing persistent worlds and show how a shared world representation supports coherent gameplay while remaining grounded in the source narrative. By explicitly reconstructing persistent worlds prior to interactive realization, this work bridges computational narrative understanding and interactive content generation, providing a semantic foundation for AI-assisted game authoring, mixed-initiative design, educational simulations, and narrative-grounded interactive experiences. --- ### CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers Authors: Mohammad Hasan Ahmadilivani, Sven-Markus Loorits, Jaan Raik Published: 2026-08-03 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2608.04035v1 The wide adoption of Vision Transformers (ViTs) in safety-critical applications raises reliability concerns related to hardware faults. Algorithm-Based Fault Tolerance (ABFT) methods have emerged as lightweight and symmetric protection mechanisms for DNNs. However, they are particularly challenging for ViTs due to their significant computational requirements. This work comprehensively evaluates the reliability of ViTs, emphasizing the need for symmetric protection in their layers. Furthermore, we present CheckOne, a novel, cost-effective method for fault detection and mitigation in ViTs that significantly reduces the computational cost compared to conventional ABFT. Through extensive experiments with multiple ViTs, CheckOne mitigates critical faults by up to $26\times$ and achieves an average 3.8x higher performance than ABFT in ViTs. --- ### Every Wrong Answer Counts: Option-Level Psychometrics for LLM Multiple-Choice Benchmarks Authors: Xiao Fei, Yang Zhang, Sarah Almeida Carneiro, Michalis Vazirgiannis Published: 2026-08-03 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.02966v1 Most multiple-choice question (MCQ) benchmarks evaluate Large Language Models (LLMs) only by whether they select the correct answers. This binary scoring treats all incorrect responses alike, even though an LLM's preferences among incorrect options may contain systematic and useful information about its behavior and ability. We introduce the LLM Nominal Response Model (LLM-NRM), an option-aware psychometric framework that models the full distribution over answer choices to jointly estimate LLM ability and option-level item characteristics, while separating model-specific response calibration sharpness, positional preference, and difficulty-dependent fallback behavior. Across 189 LLMs and 31,554 items from 14 benchmarks, LLM-NRM predicts held-out LLM-item interactions more accurately than binary Item Response models and conventional nominal-response baselines, and its ability estimates achieve the strongest Spearman correlation of 0.920 with the external human-preference Arena.ai Elo leaderboard. Distractor identity contributes +101% additional Fisher Information per item beyond correctness, and incorrect responses alone recover full-information ability estimates with Spearman 0.943. The learned item parameters also enable efficient benchmarking, where 41 selected items preserve the full-bank ranking with Kendall's correlation 0.85, corresponding to a 770 times reduction. In conclusion, we show that incorrect answers carry distinct and useful measurement information rather than representing equivalent mistakes. --- ### A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics Authors: Yachao Zhu, Qiujie Huang, Sinan Li, Yang Li, Gang Lei, Jianguo Zhu Published: 2026-08-03 Categories: cs.LG, cond-mat.mtrl-sci, eess.SY arXiv: https://arxiv.org/abs/2608.02965v3 Magnetic components in high-frequency, high-power-density converters are increasingly driven by non-sinusoidal flux-density waveforms with fast transitions, minor-loop operation, dc bias, and temperature variation. Under these conditions, steady-state core-loss formulas and single-valued material curves cannot fully capture transient magnetization responses. This work proposes the Physics-Informed Hybrid Neural Operator (PI-HNO), a compact material-specific neural model with B-H energy-consistency regularization for core-loss-oriented transient magnetization prediction. Given the measured B(t)-H(t) history, the input B(t) series over the prediction interval and operating-condition information, PI-HNO predicts the H(t) series and the corresponding reconstructed B-H trajectory. The model integrates a local recurrent branch for boundary-state representation and rate-dependent response evolution with a Preisach-inspired global branch that extracts waveform-level hysteresis context. Evaluation on the MagNetX transient database using material-specific models for 14 ferrite materials demonstrates that PI-HNO achieves a compact trade-off between sequence accuracy and B(t)-H(t) energy consistency, with the mean and 95th percentile B(t)-H(t) energy consistency errors of 1.92% and 7.60%, respectively, using only 4777 trainable parameters per model. Ablation studies further demonstrate that the local, global, and energy-aware regularized components provide distinct contributions to transient magnetization prediction. --- ### A Physics-Informed Hybrid Neural Operator for Transient Magnetization Prediction in Power Magnetics Authors: Yachao Zhu, Qiujie Huang, Sinan Li, Yang Li, Gang Lei, Jianguo Zhu Published: 2026-08-03 Categories: cs.LG, cond-mat.mtrl-sci, eess.SY arXiv: https://arxiv.org/abs/2608.02965v1 Magnetic components in high-frequency, high-power-density converters are increasingly driven by non-sinusoidal flux-density waveforms with fast transitions, minor-loop operation, dc bias, and temperature variation. Under these conditions, steady-state core-loss formulas and single-valued material curves cannot fully capture transient magnetization responses. This work proposes the Physics-Informed Hybrid Neural Operator (PI-HNO), a compact material-specific neural model with B-H energy-consistency regularization for core-loss-oriented transient magnetization prediction. Given the measured B(t)-H(t) history, the input B(t) series over the prediction interval and operating-condition information, PI-HNO predicts the H(t) series and the corresponding reconstructed B-H trajectory. The model integrates a local recurrent branch for boundary-state representation and rate-dependent response evolution with a Preisach-inspired global branch that extracts waveform-level hysteresis context. Evaluation on the MagNetX transient database using material-specific models for 14 ferrite materials demonstrates that PI-HNO achieves a compact trade-off between sequence accuracy and B(t)-H(t) energy consistency, with the mean and 95th percentile B(t)-H(t) energy consistency errors of 1.92% and 7.60%, respectively, using only 4777 trainable parameters per model. Ablation studies further demonstrate that the local, global, and energy-aware regularized components provide distinct contributions to transient magnetization prediction. --- ### Material-Segmented Per-Pixel Emissivity Correction for Thermographic Anomaly Detection in Cultural Heritage Digital Twins Authors: Jonathan Klingspon, Scott McAvoy, Maurizio Seracini, Falko Kuester Published: 2026-08-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.02964v1 Quantitative longwave thermography of heritage surfaces is limited by the global-constant emissivity assumption in inverse-Planck temperature retrieval; on heterogeneous surfaces emissivity varies within one field of view, producing apparent-temperature artifacts that mimic and mask subsurface anomalies. We present a training-free pipeline that derives per-pixel emissivity by applying SAM 3.1 open-vocabulary segmentation to a colocated, co-calibrated RGB channel, mapping segments to a material-keyed LWIR emissivity table compiled from primary measurement literature, and propagating the field into a per-pixel inverse-Planck solve on raw radiometric data. Lacking any public dataset with raw radiometry, a temperature reference, and a colocated RGB camera, we evaluate on a physics-based synthetic benchmark and four real datasets. On the benchmark, under a palette spanning the low-emissivity exceptions, the correction cuts mean absolute error from 1.97 K to 0.91 K at 20 K contrast and, with an accurate table, beats the best fitted global constant on every layout; on a heritage-realistic emissivity distribution it does not. We contribute a quantified operating-regime map, and a measurement-backed finding that tempers the heritage claim: weathered outdoor heritage emissivities cluster near the conventional default, so the correction is small on typical surfaces and concentrated on genuine low-emissivity exceptions. We characterize the dominant failure mode, in which open-vocabulary segmentation matches appearance rather than material, and the contraindicated regime in which emissivity-defined anomalies are suppressed. --- ### Scaling an Autoregressive Transformer for Single-Cell Generation Authors: Aleksandr Sharipov, Yusif Mukhtarov, Igor Molybog Published: 2026-08-03 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2608.02961v2 We study a self-supervised generation task for single-cell gene expression vectors: given a set of vectors from a cell type, we aim to generate additional gene expression vectors of that cell type. For this task we characterize both the biological fidelity of the generated gene expression vectors and the scaling behavior of the pretraining loss. The model is a causal transformer paired with a learned quantized VAE tokenizer, trained with a cross-entropy loss. To evaluate the model, we condition it on held-out gene expression vectors of a cell type and generate vectors of gene expression, comparing the resulting distribution over gene expression vectors to the ground truth distribution of that cell type. We study the scaling properties of the proposed architecture by varying the number of trained parameters and the amount of training data. To our knowledge, we find the first jointly-fit two-exponent scaling law and compute-optimal frontier for a single-cell foundation model. Finally, we discuss how this pretrained model could be finetuned for perturbation response prediction. --- ### Scaling an Autoregressive Transformer for Single-Cell Generation Authors: Aleksandr Sharipov, Yusif Mukhtarov, Igor Molybog Published: 2026-08-03 Categories: cs.LG, cs.AI, q-bio.GN arXiv: https://arxiv.org/abs/2608.02961v1 We study a self-supervised generation task for single-cell gene expression vectors: given a set of vectors from a cell type, we aim to generate additional gene expression vectors of that cell type. For this task we characterize both the biological fidelity of the generated gene expression vectors and the scaling behavior of the pretraining loss. The model is a causal transformer paired with a learned quantized VAE tokenizer, trained with a cross-entropy loss. To evaluate the model, we condition it on held-out gene expression vectors of a cell type and generate vectors of gene expression, comparing the resulting distribution over gene expression vectors to the ground truth distribution of that cell type. We study the scaling properties of the proposed architecture by varying the number of trained parameters and the amount of training data. To our knowledge, we find the first jointly-fit two-exponent scaling law and compute-optimal frontier for a single-cell foundation model. Finally, we discuss how this pretrained model could be finetuned for perturbation response prediction. --- ### ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies Authors: Inkyu Sa, Konstantin Stulov, Rajat Bhageria Published: 2026-08-03 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.02958v1 Vision-Language-Action (VLA) policies trained by behavior cloning fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress. Reinforcement learning would supply one, but it is impractical here, where real-robot experience is costly and deformable food resists simulation. The cheap alternative, a terminal success / failure bit, is learnable in principle yet far too sparse to say when a rollout went wrong. We argue that the per-frame label, not the architecture, is the hard part: to be useful it must be dense, continuous, and correctly shaped. We present ValueFormer, a compact policy-agnostic causal transformer over a frozen DINOv3 backbone that emits two per-frame signals in one forward pass: a smooth Monte Carlo value, V_mc, for advantage estimation and a sharp binary value for online mistake detection, targets that pull in opposite directions by design. Failed episodes are labeled with a stage-aware, success-then-decay return that preserves the success curve before the failure stage, and detection is supervised from mistake intervals rather than a single failure time, so mistakes the policy recovers from also carry signal. On a real-robot bimanual sandwich-assembly task 1,427 episodes), a critic-derived per-frame training weight lifts task completion from 70% to 85% (within noise at n=20), and a batched bf16 encoder cuts the live serving cost 3~5 times so the critic runs at 2 Hz alongside the policy on a single GPU. ---