# Research Papers — 2026-07 · bundle page 1 of 222

> Full-text markdown of papers #1–50 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-07
[Next bundle →](https://aipod.dev/papers/archive/2026-07/page/2.md)

### From Prediction to Explainable Provider Behavior Profiles for Fraud, Waste, and Abuse Review

Authors: Yubin Park, Evan Brociner
Published: 2026-07-31
Categories: cs.CY, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2609.28477v1

Claims data can show that provider behavior changed but cannot by itself explain why. FWA (fraud, waste, and abuse) review requires identifying material behavior, locating the codes and dollars driving it, and testing plausible explanations. A common alternative, predictive modeling, flags deviations from an expected-utilization forecast -- but a forecast has limited value unless it beats simple persistence and explains why a deviation matters. In our quarterly provider-procedure data, the latest observation captures most forecastable variation, and added model structure adds little accuracy. Residuals conflate growth, service-line shifts, code maintenance, and incomplete observation with potentially concerning behavior, making point forecasts incomplete. We instead formulate provider review as a descriptive representation problem: billed revenue y = s * p, where s measures provider scale and p describes procedure composition. The profile records scale history, effective-dated code lineage, clinical-family shares, first-use events, billing context, and Medicare-versus-client differences. An optional rank-32 nonnegative factorization of procedure co-occurrence adds a fixed semantic geometry for similarity and retrieval, surfacing evidence for review without inferring intent or adjudicating FWA. In an eight-quarter proprietary Medicare Carrier+DME audit of 1.22 million providers, simple descriptions outperform complex forecasts: regularized AR(1) attains the lowest log MAE, while persistence attains the lowest dollar WAPE. The learned semantic dictionary raises recall at 10 from 35.9% to 44.7% and high-cost-rare recall at 50 from zero to 51.8%. A lineage-aware family profile stays compact and interpretable, correlating 0.790 with learned-state movement, supporting a layered architecture where transparent descriptions form the core and learned representations add optional context.

---

### A Vision-Language Framework for Measuring Social Life on Sidewalks

Authors: Liu Liu, Andres Sevtsuk
Published: 2026-07-31
Categories: cs.CY, cs.CV
arXiv: https://arxiv.org/abs/2609.28476v1

While a number of methods exist for counting pedestrians in street-view imagery, these mostly ignore the social dimensions of pedestrian activity. A street traversed by a high volume of pedestrians has the same headcount as a street where people linger, sit, and socialize. This paper presents a vision-language framework for extracting social indicators from street-level imagery. Panoramic street-level imagery is reprojected to sidewalk-facing sideviews with preserved timestamps. A vision-language model (VLM)-based activity detection system codes each person across ten independent observable dimensions, resolving a systematic failure mode in which models prompted with high-level social categories conflate observable states with contextual inferences. The resulting social indicator system produces a Social Dwelling Index (SDI) that jointly considers pedestrian grouping and dwelling, provides activity labels documenting behavioral diversity, and issues binary flags for the presence of accessibility-sensitive populations. We apply the framework to 102,514 sideviews in New York City, revealing that pedestrian volume and SDI are only weakly associated (r = 0.168): streets with the highest foot traffic are not where social activity is most intense. The framework provides a scalable method for measuring not only how many people are on city sidewalks, but also their grouping, posture, and activity type, summarizing the non-transient activities that occur on city sidewalks.

---

### A Computational Approach to Measuring Semantic Change in Sanskrit Literature

Authors: Tanay Agrawal
Published: 2026-07-31
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.25012v1

Diachronic word embeddings have become the modern standard for tracking semantic change, yet they have been largely validated on modern, high-resource, and well-segmented languages. This paper tests whether the paradigm transfers to Sanskrit, an ancient, low-resource language whose phonological fusion (sandhi), morphological inflection, compounding, and polysemy pose a unique challenge. I assemble a 2.7M-token corpus spanning four canonical periods, recover word boundaries with a neural byte-level sandhi splitter and lemmatizer, and train per-period embeddings across configurations. To evaluate the system, I curate a validation set from historical scholarship and test recovery directionally with anchor displacement. Of 21 testable shifts, 19 move in the philologically attested direction (sign test, p=0.00011). I further show which configuration the language forces and comment on opportunities for improvement.

---

### Functional Emotion Without Character: Large Language Models, Aristotelian Disposition, and the Limits of Behavioral Alignment

Authors: Marzieh Zare
Published: 2026-07-31
Categories: cs.CL, cs.CY, cs.HC
arXiv: https://arxiv.org/abs/2609.22362v1

Debates about whether artificial systems can feel are often forced between two unsatisfactory positions: behavioral equivalence is treated as sufficient for emotion, or phenomenal consciousness is treated as a prerequisite that makes the question empirically inaccessible. This article develops a structural alternative. It models emotions as context-sensitive regions, trajectories and attractor dynamics in high-dimensional representational state spaces. Recent mechanistic interpretability findings support the existence of causally active emotion-concept representations in large language models, but they do not establish subjective feeling or full emotional agency. Assessed against published adequacy standards for representation in language models, intervention provides strong evidence of causal use, while full affective role integration, uniformity across subject domains and coherence remain only partially established; there is no direct analogue of accuracy. These mismatches expose the need for a standard of affective appropriateness, which an account of character must supply. Such an account requires three further conditions: regulatory embodiment that gives valence endogenous stakes, temporal continuity that allows affective episodes to accumulate into a history, and an integrated self-model that binds that history to persistent values. Aristotle's concepts of pathē, hexis, mesotēs and phronēsis are translated into a state-space sketch in which practical wisdom includes competence in estimating normatively salient context, not merely acting on a context description already given. The framework reframes alignment as a problem of durable disposition rather than output conformity, and yields interventional tests with explicit control conditions.

---

### QEncodeBench: Can Large Language Models Encode Classical Problems into Verified Quantum Oracles?

Authors: Xujun Che, Hanhan Wu, Yuchen Yuan, Chenyang Yu
Published: 2026-07-31
Categories: quant-ph, cs.LG
arXiv: https://arxiv.org/abs/2609.20319v1

Grover search, amplitude amplification, and quantum counting all rely on the same reusable subroutine, a phase oracle, whose construction the algorithms literature takes as given: the classical predicate is assumed to be already encoded as a correct, resource-bounded circuit. We turn this assumption into a measured capability. QEncodeBench tasks large language models (LLMs) with encoding classical constraint problems as phase oracles and scores the generated circuits with an adversarially self-validated verifier that decides full solution-set equivalence up to a global phase, with ancillas restored and resource budgets enforced. Sampled basis-state tests, we show, systematically overestimate this ability. Measured this way, models separate sharply: code models without a reasoning mode solve essentially nothing, and enabling native reasoning on identical weights improves accuracy by an order of magnitude. The failures are overwhelmingly semantic rather than syntactic. Two architectures, a unit-verified constraint agent and a neuro-symbolic compilation pipeline, close most of the remaining gap by delegating correctness-critical composition to deterministic procedures. Ablations quantify the contribution of each component, and resource gating exposes an architecture-dependent trade-off between circuit width and depth. Finally, controlled difficulty escalation reveals architecture-specific responses to difficulty structure: different difficulty axes degrade different methods, while the neuro-symbolic pipeline passes every evaluated instance. Code and data are available at https://github.com/chexujun/QEncodeBench.

---

### LLM-Guided Transformation of Non-Critical Driving Scenes into Safety-Critical Scenarios Using Augmented Reality

Authors: Noura Fady, Farah Khaled, Catherine M. Elias
Published: 2026-07-31
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2609.20318v1

Testing Autonomous Driving Systems (ADS) requires realistic safety-critical scenarios, but collecting such data from real-world driving is costly and unsafe. This paper presents an automated pipeline that transforms safe driving scenes into safety-critical scenarios by combining computer vision, Large Language Models (LLMs), and Augmented Reality (AR). The system detects and tracks road users, extracts safety features including distance, velocity, motion direction, and Time-to-Collision (TTC), and assesses scene criticality. Safe scenes are modified by an LLM, which generates realistic collision-inducing objects and behaviors that are integrated into the original scene using AR. The proposed pipeline was evaluated on the nuScenes dataset, achieving 97.52% safety classification accuracy and successfully generating realistic scenarios such as pedestrian crossings, rear overtaking vehicles, and sudden-stop events. The results demonstrate an effective and flexible approach for automated generation of safety-critical scenarios to support the testing and validation of autonomous driving systems.

---

### EviRec: Continual Evidence Learning for Dual Cold-Start POI Recommendation

Authors: Rongchao Xu, Lin Jiang, Guang Wang
Published: 2026-07-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20313v1

Point-of-Interest (POI) recommendation is a core task in location-based services, yet most existing methods assume a fixed user population and POI catalog. Through a large-scale data-driven analysis of 10 U.S. cities, we identify substantial POI churn, user turnover, category drift, and decay in static POI memory, motivating the study of continual dual cold-start POI recommendation. To address this setting, we propose EviRec, a continual evidence-learning framework that estimates how much historical evidence should be trusted separately for each candidate POI. EviRec scores each visible candidate from three complementary views: a matching view based on the user's recent mobility profile, a transition-memory view that captures repeated mobility routines, and a lifecycle view that reflects candidate maturity. Because a near-zero transition score may indicate either irrelevance or insufficient observation, EviRec qualifies the evidence using each candidate's observation state and applies a reliability gate to adaptively route between transition-memory and lifecycle evidence. We evaluate EviRec on a full-year, five-city POI check-in dataset containing more than 30,000 users and 684,200 trajectories. Experimental results show that EviRec consistently outperforms state-of-the-art baselines, with the largest gains concentrated on cold-start queries. In particular, EviRec improves NDCG@10 by 20.4\% on Dual-New cases over the strongest baseline. In-depth analyses further confirm that these gains arise primarily from candidate-specific reliability gating while largely preserving previously learned mobility routines.

---

### Human and AI-generated texts between modal logic and statistics

Authors: Simone Cuconato, Donato Ferrari
Published: 2026-07-31
Categories: math.LO, cs.AI, math.ST
arXiv: https://arxiv.org/abs/2609.20311v1

We read the geometry of semantic neighbourhood graphs as modal logic and give that reading a statistical form, in order to make precise the structural difference between human and machine-generated text. Texts are the worlds of a finite frame whose accessibility is the $k$-nearest-neighbour relation of a transformer embedding, and the symmetry, transitivity, Euclideanity and seriality frequencies of the two subcorpora are shown to be degrees of validation of the modal axioms $\mathsf{B}$, $\mathsf{4}$, $\mathsf{5}$, $\mathsf{D}$. Each degree is at once the proportion of instances of a rule that the subframe licenses in Negri's labelled calculus $\mathsf{G3.K}$ and a plug-in estimate of a population probability. A prompt-balanced comparison finds consistently higher artificial degrees for $\mathsf{4}$ and $\mathsf{5}$. We add a degree of groundedness and of situatedness, and recast the licensing reading in Cuconato's one-sided sequent-style tableaux, where each degree becomes a rate of set membership.

---

### ZeroHAT: Behavior-Conditioned Zero-Shot Human Activity Trace Generation

Authors: Rongchao Xu, Dahai Yu, Lin Jiang, Guang Wang
Published: 2026-07-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20310v1

Human activity traces record individuals' timestamped visits to points of interest and are essential for applications such as mobility prediction and urban simulation. However, accessing large-scale HATs is challenging due to high collection costs and privacy concerns. Synthetic HAT generation offers a promising way to make such data available and has attracted growing interest from both industry and academia. Although many efforts have been devoted to this topic, most of them rely on real data from a region to generate synthetic data for the same region, which is infeasible for the many regions where real HATs are unavailable. To fill this gap, we propose ZeroHAT, a behavior-conditioned framework that generates synthetic HATs for a target region in a zero-shot manner by transferring behavioral patterns learned from real HATs in source regions and adapting them with publicly available contextual information about the target region. ZeroHAT has three key novel components: (i) a multidimensional consistency-aware intent extractor; (ii) a cross-region behavioral cloning module; and (iii) a behavior-conditioned activity realization module. We evaluate ZeroHAT on a ten-city benchmark, where extensive experiments show that ZeroHAT achieves 4.5-6.4x the normalized downstream utility of the strongest baseline and improves average fidelity by 15.6%-40.8% across target regions.

---

### Hypernetwork-Parameterized Spatially Adaptive Neural Operators for PDE Learning

Authors: Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Meng Ye, Xiaofeng Zhang, Qiang He, Weifeng Huang, Guoqing Wang, Yang Yang, Caiyan Qin
Published: 2026-07-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20309v1

Spatially heterogeneous partial differential equations (PDEs) exhibit location-dependent dynamics arising from variations in geometry and physical coefficients. Existing neural operators improve localized modeling through multiscale features, attention mechanisms, or domain decomposition, yet their update rules often remain spatially shared. Hypernetwork-based methods adapt parameters across PDE instances but typically generate only one global parameterization per instance. Consequently, shared operators may underfit boundaries and high-gradient regions, with these localized errors accumulating during autoregressive rollout. We propose a spatially adaptive neural operator (SANO), which replaces this spatially shared parameterization with a spatially continuous field of location-dependent operator parameters. SANO uses Fourier-encoded coordinates and a coordinate-conditioned hypernetwork to generate spatial operator-conditioning codes at sampling points. A Hyper-Neural Element (HNE) mechanism interpolates these codes within local subregions, coupling neighboring operators while allowing their update rules to vary across space, and partition-of-unity weights assemble the overlapping local predictions. Experiments on one-, two-, and three-dimensional PDEs and two perforated-domain elliptic benchmarks show that SANO consistently outperforms competitive neural-operator, hypernetwork-based, and physics-informed baselines.

---

### Intact-to-Amputee Transfer in Surface-EMG Gesture Decoding: Training Source and Calibration Budget

Authors: Jethro Odeyemi, W. J. Zhang
Published: 2026-07-31
Categories: cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2609.20297v1

A recogniser trained on one person rarely transfers to the next, and useful performance usually demands a fresh round of labelled calibration from the end user. A systematic review of 1077 studies quantifies where the evidence is thin: amputees appear in about one in six. Here a montage-agnostic cross-user encoder is carried to eleven transradial amputees on a protocol matched to its intact-limb training data. Zero-shot cross-population transfer fails outright: the encoder requires labeled data from the new user before it begins decoding, and it then exceeds the per-user classifier a clinic would fit by 0.190 macro F1 at three repetitions and for every subject in the cohort. Given three labelled repetitions it reaches 0.779 macro-F1 against 0.589 for the per-user pipeline. Training on forty intact subjects produces better transfers to a new amputee than training on ten other amputees, and combining the two produces better transfers than either individually. The prediction pre-registered for this study, which extends the encoder's baseline-strength account with the premise that amputee EMG is less separable, holds true only after a few repetitions become available and after enriching the source pool with additional amputees. At a single repetition, and at every budget under a source matched to the intact-limb comparison, it fails. Thus, it locates the boundary of the proposed account.

---

### Personalising a Cross-User Surface Electromyography Encoder Under a Small Calibration Budget

Authors: Jethro Odeyemi, W. J. Zhang
Published: 2026-07-31
Categories: cs.LG, cs.HC
arXiv: https://arxiv.org/abs/2609.20296v1

A myoelectric interface needs calibration from the user before it will function. Earlier work has treated calibration as a quantity, but has not asked the question of what a device should do with the calibration repetitions once they have been collected. This paper views personalizing the cross-user encoder as a design decision with a cost. Four alternative approaches to using exactly the same labeled repetitions were tested from a single cross-user encoder per held-out subject. Prototypical adaptation, linear probes, scaled fine-tuning and full fine-tuning were tested at every budget up to the maximum each database allows, five repetitions on DB1 and four on DB2 and DB5. Comparing four ways to spend a small calibration budget across 77 subjects, full fine-tuning is the most accurate at every budget, consistently enough that there is no exception among subsets of subjects. The result which impacts how one might make an engineering decision however is that a gradient free prototypical rule recovers 52 to 78 per cent of its benefit with no optimiser and no per-user copy of the weights, which makes personalisation something a worn device can do at donning time. The widespread intuition that a good representation only needs a fresh classifier is incorrect here. How well each method may perform relative to a per-user classifier that would be fitted by a clinic will depend on the specific database.

---

### Temperon: Full-Time SAM Quality at a Third Less Wall-Clock

Authors: Stamatis Mastromichalakis
Published: 2026-07-31
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2609.17575v1

Sharpness-aware minimization (SAM) doubles the cost of every training step, yet its benefit concentrates where training ends. We study where an expensive training mode should be spent and propose Temperon: a plain-SGD explorer for the first 43% of the epoch budget, then one scheduled hand-off that gives the entire final cosine anneal to a SAM-wrapped Muon refiner. On CIFAR-10/100, SVHN and Tiny ImageNet (five seeds, times reported as epochs-to-target times an idle-GPU-calibrated epoch cost), Temperon matches the best full-time-SAM recipe on accuracy everywhere while reaching the hardest common target 35%, 34% and 32% sooner on three of the four, and sits a tier above the published SAM+SGD recipe at level cost. Ablations make the attribution exact: the Muon refiner is worth +0.85pp with everything else fixed; the explorer's shape and its restarts are worth nothing, and we withdraw them as contributions. Re-running the closest rival, late-phase SAM, at matched budget shows the frontier: it is fastest to every mid-level target, but the tier the Muon refiner buys (0.83 on CIFAR-100, 0.97 on CIFAR-10) is reached by no SGD-refined method in any seed, and on Tiny ImageNet, where Muon buys no tier, the rival simply wins -- the measured boundary of the method. The allocation law transfers to GPT-2 pretraining (full-SAM quality at -29% wall-clock) and GLUE fine-tuning (never worse than full-time SAM at a third of its SAM cost). Two constants organize the economics: skipping SAM early buys a fixed credit, and a Muon epoch costs 1.50x a SAM+SGD epoch on all four datasets. Finally, the hand-off cannot be timed from the trajectory: under cosine schedules the accuracy curve is plateau-then-surge, so the information lives in the schedule, making the scheduled switch principled rather than convenient. Code and a pip-installable implementation are released.

---

### Recovery Rates Are Not Comparable Across Transcription Factors: Chance Correction for Attribution Evaluation

Authors: Hyunkyung Han, Min Jung Kim
Published: 2026-07-31
Categories: q-bio.OT, cs.AI
arXiv: https://arxiv.org/abs/2609.16271v1

Attribution methods for genomic sequence models are commonly evaluated by how much of a known motif they recover, or by how a prediction degrades as evidence is deleted. Neither score is interpretable without the value it would take by chance, and neither is routinely reported against one. We show that this omission is not a matter of precision but of validity. The uniform chance level for contiguous motif overlap is \(L/(N-L+1)\); across 268 transcription factors in UniBind it ranges from 0.0118 to 0.0427, a 3.6-fold spread determined by motif length and window size alone. For two factors the bootstrap intervals of the chance levels themselves do not overlap, so their raw recovery rates are not comparable quantities. Correcting for this dissolves a published three-way classification of five factors: a factor reported as a resolution failure attains the second-highest corrected value, ahead of one of the two positive controls, and two reported as complete failures fall at or below chance. We further show that perturbation-based evaluation can fail its own precondition: for one factor a fully masked input still scores above the decision boundary, and the curve is not monotone in the number of masked positions, so the area under it is not a measure of faithfulness. We provide chance levels in closed form, a chance-corrected score, and two screens that run before any attribution is computed.

---

### Position: AI Is Not Ready for Strategic Conflicts

Authors: Mark Riedl, Glenn Matlin
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.16189v1

Open-ended strategic wargames are high-stakes LM-based social simulations: they model adversaries, institutions, escalation, plan brittleness, doctrine, and crisis response. Language models (LMs) are attractive because they can play agents, generate scenario branches, adjudicate ambiguous actions, and summarize lessons, but the same affordances make open-ended roles dangerous: model language determines both what an actor attempts and what becomes simulated reality. This position paper argues that no LM-enabled wargame should inform planning, doctrine, policy, or crisis response without an auditable safety case, and that the proper use of open-ended wargames today is to stress-test decision-influencing LM agents. We identify five failure modes: decision laundering, adjudication opacity, role collapse, escalation-through-adjudication, and failure of strategic imagination. Ordinary benchmarks cannot establish safety for these settings. Wargames can expose failures as stress tests; they are not themselves safety cases for consequential use.

---

### Z-Loss Backward Geometry in Dense Output Heads and Sparse Routers

Authors: Bum Jun Kim
Published: 2026-07-31
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2609.16179v1

Z-loss has been widely applied to the logits of language-model output heads and sparse mixture-of-experts routers. Z-loss constrains the softmax log-normalizers of these output heads and routers, thereby limiting large-logit excursions, reducing finite-precision roundoff exposure, and avoiding training-loss divergence. These use cases arise in modern Transformer settings where large-vocabulary softmax heads, top-$k$ routing, fused losses, and mixed-precision optimizers interact. Z-loss has typically been understood only as a scalar penalty on the log-normalizer. This paper instead analyzes Z-loss from a backward-pass perspective, focusing on the gradients produced by the Z-loss penalty. The logit-space gradient, which we call the backward source, is injected at the logit boundary of the Z-loss branch of backpropagation; consequently, the backward source's effect depends on the architecture and implementation through which the gradient is transported. We develop a backward-transport view for Z-loss that separates the source's scalar amplitude and softmax shape from the transport factors. These factors include common-shift coordinates, tied-embedding pathways, output-to-hidden gain, fused-loss source consistency, optimizer-facing updates, and top-$k$ router reduction scale. These diagnostics show that nearly identical forward Z-loss values can coexist with distinct logit-space Z-loss gradients and, after architectural and optimizer transport, distinct parameter updates. The transport diagnostics also explain why raw-logit Z-loss can reduce scalar tails without changing output-to-hidden gain and why active-route reductions alter the effective router coefficient. Across evaluations of models in the GPT-2 and Pythia families on WikiText-103 and FineWeb-Edu, architecture-aware variants reduce backward-geometry tails while maintaining comparable validation perplexity in low-coefficient regimes.

---

### LLMs or Naive Bayes? Old Gems or New Ways

Authors: Mohammad Firas Sada, Dmitry Mishin, John Graham, Seungmin Kim, Mahidhar Tatineni, Frank Würthwein
Published: 2026-07-31
Categories: cs.LG, cs.AI, cs.CL, cs.DC
arXiv: https://arxiv.org/abs/2609.13185v1

Large language models (LLMs) prompt a recurring question in research computing: should classical methods like Naive Bayes (NB) be retired? We benchmark Complement Naive Bayes against zero-shot and few-shot LLMs spanning four model families and a 37x range in scale (27B to a 1T-parameter mixture-of-experts) across text classification tasks. LLMs dominate only in zero-data regimes (98.0% vs 88.2% on Amazon Polarity sentiment), and even that win is contamination-prone: on a low-contamination sentiment task NB beats the zero-shot LLM (81.7% vs 73.0%). However, once labeled data is available (e.g., AG News), NB reaches 89.1% accuracy, statistically indistinguishable from the zero-shot 27B LLM (89.0%) and better than the 397B frontier model (84.8%), at thousands of samples/sec on a commodity CPU. Fine-tuned DistilBERT reaches 90.6% but at far lower throughput than NB at batch size 1 (Table 2). Our measured GPU throughput analysis shows small-LLM batched inference is 40-486x slower than NB CPU inference (the multiplier depends strongly on the host CPU), exposing a structural gap bounded by memory bandwidth, with roughly two orders of magnitude lower energy per sample. For resource-constrained HPC practitioners performing text classification with labeled data, NB remains the optimal choice. We show the decision line is task-dependent (NB reaches LLM parity around $N \sim 10^4$ labels for topic classification, while zero-data sentiment favors the LLM at all N tested) and provide a Kubernetes Helm operator that automates model selection using configurable thresholds and verifiable Prometheus metrics.

---

### Efficient AI Model Deployment Using Quantization Analysis Tool

Authors: Dwith Chenna, Kanishka Macherla
Published: 2026-07-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.11954v1

As deep learning models are increasingly deployed on resource constrained devices, the demand for efficient model optimization techniques continues to grow. Effective deployment of AI models on edge and low power platforms requires optimization methods that reduce model size and computational cost while maintaining high accuracy. This paper presents Quantization Analysis Tool, a practical system designed to streamline quantization workflows and support performance efficient model deployment. Built on the ONNX framework for broad interoperability, the tool provides detailed layer-wise sensitivity analysis, visualization of weight and activation distributions, and insights to guide precision selection. By identifying layers that are resilient or sensitive to reduced precision, the tool enables developers to make informed trade-offs between model size, latency, and accuracy. Experimental evaluations across multiple neural network architectures demonstrate that the tool effectively improves the quantized accuracy, leading to improved efficiency in real-world deployment scenarios. The tool also provides developers valuable insights into the effects on quantization on the model and its accuracy. This work highlights the tools capabilities, practical applications, and its role in enabling efficient AI model deployment through robust quantization analysis

---

### AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents

Authors: Adib Hasan, Daniel Schaffield, Akashnil Dutta, Tarik Adnan Moon
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.05446v1

We introduce AutoFyn, an agent harness inspired by the Expert Iteration algorithm, adapting a frozen model across many rounds by updating persistent state from verified reward signals rather than model weights. Each round begins from a fresh model session, and durable information is reintroduced only through explicit interfaces such as persistent memory files, reports, and repository state. Within a round, an orchestrator explores, plans and builds many alternative approaches with specialized agents, while a task-grounded verifier verifies the work and supplies an objective reward for measuring progress. This reward is distilled back into the persistent state, which updates the effective policy for the next round. In this technical report, we formalize this loop and describe its persistent state and verification interfaces. We then demonstrate its use in three domains, namely olympiad mathematics, data science, and cybersecurity. On the six fresh problems of the 2026 International Mathematical Olympiad, every model with room to improve scores higher under AutoFyn than in its provider's own coding agent. AutoFyn also built the top-ranked agent on the Spider 2.0 dbt benchmark, and has produced $16$ maintainer-confirmed vulnerability advisories in Next.js, MetaMask, pnpm, Warp, LiteLLM, Langflow, and Open WebUI.

---

### CDEP Agent: Connecting Meteorologically Detected Temporal Compound Events to Real-World Documentary Evidence

Authors: Zhuoran Li, Weiyi Kong, Boer Zhang
Published: 2026-07-31
Categories: cs.AI, cs.CY, physics.ao-ph
arXiv: https://arxiv.org/abs/2608.28628v1

Compound drought-to-extreme-precipitation (CDEP) events are recognized in climate science as a growing driver of extreme impact, but whether this recognition carries over into real-world early warning and post-event documentation is unknown, so a meteorologically real CDEP event may pass with neither advance warning nor any later record. Here we present CDEP Agent, an auditable LLM-agent framework that tests this mismatch directly by linking CDEP candidates detected from meteorological reanalysis to real-world hazard and impact evidence across sources with different spatial scales, temporal resolutions, and reporting conventions. Using California as a case study, we identify 408 candidate CDEP events from ERA5 observations during 2021-2025 and evaluate each against the U.S. Drought Monitor, NOAA Storm Events, and public webpages along five dimensions: antecedent drought, extreme rainfall, local impact, hazard-impact attribution, and explicit drought-to-rainfall linkage. Only 34.3% of candidates are corroborated on both hazard components, and just 1.5% are ever explicitly linked to their antecedent drought, indicating that most meteorologically detected CDEP events go undocumented and their compound nature almost never enters the record at all. Our framework gives climate scientists a way to test physical event definitions against what actually gets documented, and gives social scientists, economists, and disaster-response agencies a provenance-linked evidence base for compound events that current warning and reporting systems largely fail to capture.

---

### Machine Learning-Enhanced Tabu Search for Tactical Wireless Network Design

Authors: Wissem Ahmed Zaid, Alain Hertz, Defeng Liu
Published: 2026-07-31
Categories: cs.AI, cs.LG, math.CO
arXiv: https://arxiv.org/abs/2608.28627v1

Designing high-performance tactical wireless networks under realistic operational constraints gives rise to challenging combinatorial optimization problems, where the evaluation of candidate solutions relies on detailed physical and traffic-aware models. Although classical metaheuristics such as Tabu Search offer effective mechanisms for exploring large search spaces, their computational cost remains high because numerous candidate moves must be evaluated at every iteration. In this paper, we propose a data-driven framework that improves the efficiency of Tabu Search by learning to guide its move selection process. Rather than altering the neighborhood structure, our approach exploits the information contained in the search trajectories generated during the optimization process. At each iteration, we record both improving and non-improving edge-based transformations together with a set of descriptive features capturing the structural, geometric, and performance characteristics of the network. This information is used to train a Graph Neural Network (GNN) that predicts the impact of candidate moves on the objective function. The trained model is then integrated into the Tabu Search algorithm to rank candidate transformations according to their predicted quality, thereby reducing the number of costly objective evaluations while maintaining an effective exploration of the search space. Experimental results on synthetic benchmark instances demonstrate that the proposed learning-assisted Tabu Search notably reduces computation time while consistently producing higher-quality solutions than the standard algorithm. These findings highlight the potential of combining machine learning with metaheuristics by leveraging the implicit knowledge embedded in search trajectories, paving the way for more efficient solution methods for large-scale network design problems.

---

### Do large language models scrutinise what they review? A multimodal audit of scoring calibration, error detection, and author-identity effects

Authors: Emad Alharbi
Published: 2026-07-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.28626v1

Large language models (LLMs) are increasingly used to generate peer reviews, prompting examination of their capacity for critical evaluation. This study evaluates two multimodal LLMs, Qwen2.5-VL-72B and Pixtral-Large-124B, as reviewers across 165 submissions to the 2026 International Conference on Learning Representations, a venue that postdates both models' training cutoffs. Manuscripts were presented to both models with author identities blinded, replaced with high-prestige affiliations, or replaced with low-prestige affiliations, and in either text-only or text-with-figure format. Additionally, 145 verifiably detectable errors were inserted into 55 manuscripts to assess error identification under natural and verification-oriented prompts. Across all manuscript groups, including rejected submissions, LLM scores ranged from 7.0 to 8.1, whereas human mean scores ranged from 3.4 to 6.8. The models detected 12.1\% of the verified errors under natural prompting, and a one-sentence verification instruction increased detection to 22.2\%; however, 78\% of the errors remained undetected. Providing figures reduced error detection while increasing review scores. No visual error was reliably verified against its corresponding figure, and half of the text-only reviews described figures that were not provided. Author identity did not influence either review scores or error detection. LLM editorial decisions exactly matched those produced by simple score averaging.

---

### Asymmetric Within-Document Predictive Learning for Scientific Document Representation

Authors: You Zuo, Éric de la Clergerie, Benoît Sagot
Published: 2026-07-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.28625v1

We study predictive pretraining for scientific document representation using the discourse structure of papers. We propose SciJEPA, a citation-free framework that learns through asymmetric within-document prediction: title and abstract representations are used to predict method representations, and method representations are used to predict conclusion representations. Experiments on RELISH, high-influence citation, SciDocs, and cite prediction show that plain predictive training is viable but weaker than a controlled contrastive baseline using the same section pairs. Adding Sliced Isotropic Gaussian Regularization (SIGReg) substantially improves performance and narrows this gap. The effect of regularization is task-dependent: moderate SIGReg helps fine-grained ranking, while stronger regularization can weaken local alignment. We further show that different encoding branches support different retrieval regimes. These results position within-document predictive learning as a promising citation-free complement for scientific document representation, provided that embedding geometry is carefully controlled.

---

### Knowledge Cards: Structured Knowledge for AI Systems

Authors: Liliana Ferreira
Published: 2026-07-31
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2608.26176v1

AI systems whose outputs inform real decisions, and increasingly consequential ones, require something that current documentation practice does not provide: a structured, inspectable representation of the knowledge they need to ground, contextualize, and reason about those decisions, ideally reviewed and signed off by a domain expert. Established documentation artefacts already capture important aspects of an AI system. Model cards describe how a system behaves, data cards describe what it was trained on, and system cards describe the risks of a deployed system. None of them addresses the layer between inputs and outputs, more precisely, the concepts a system holds, the relationships it models, and the patterns of reasoning it applies. For pattern-recognition tasks this gap is tolerable. For agentic AI, where systems act on their conclusions, it is the step that most often separates a promising proof of concept from an operational solution an organisation can rely on. This paper introduces the Knowledge Card, a structured artefact that captures validated knowledge about a single bounded concept in a form that experts can review, organisations can audit, and AI systems can reason over. For one concept, such as a specific failure mode, a compliance obligation, or a process decision, a Knowledge Card records the entities and relationships involved, the reasoning that connects them, the conditions under which that reasoning no longer holds, and the provenance of every claim, all grounded in a formal domain ontology and signed off by a domain expert. Initial prototype cards have been built in the energy and pharmaceutical domains. The schema is released as a public draft for community engagement.

---

### A Survey Instrument to Assess Students' AI and Generative AI Knowledge

Authors: Aditya Johri, Cory Brozina, Akriti Bagale
Published: 2026-07-31
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2608.21391v1

In this research-to-practice paper we present a survey that can be used to assess students' AI knowledge. As the use of artificial intelligence (AI), including generative artificial intelligence (GenAI), has proliferated, so has the need to educate students about the topic. A range of AI literacy frameworks have been proposed, outlining the essential knowledge that students should have. Alongside, different ways of assessing AI knowledge have been developed. As yet, there is a lack of assessment instruments capable of evaluating multiple forms of student knowledge, including technical concepts, practical applications, and ethical concerns about AI use. In this article, we present a study implementing a comprehensive instrument to assess AI knowledge. The instrument combines measures from multiple scales to capture a range of literacy features and actual knowledge. We implemented the instrument in a higher education setting to assess its viability and usefulness and found that the instrument exhibited useful diagnostic capabilities and was able to identify common misconceptions among students. Although students performed well overall, there was a significant misunderstanding of how AI, especially GenAI systems, work. It also identified a lack of higher-level knowledge. The instrument is publicly available for use by others. We foresee its usefulness as a diagnostic that goes beyond understanding students' attitudes and perceptions of AI and GenAI use and tests multiple aspects of students' knowledge and conceptual understanding. This can enable the development of targeted instruction.

---

### Sparse Coverage: Semantic Center Representations for Patent Prior-Art Retrieval

Authors: You Zuo, Kim Gerdes, Éric de la Clergerie, Benoît Sagot
Published: 2026-07-31
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2608.16918v1

Patent prior-art retrieval is a recall-oriented search task over long and highly structured technical documents. Dense retrieval improves semantic matching, but single-vector representations may compress multiple technical components, functions, and constraints into a single embedding. We propose Sparse Coverage, an unsupervised semantic retrieval framework that maps local span embeddings to a sparse vocabulary of embedding-space centers. The centers are selected with a coverage-oriented k-center objective, and spans activate nearby centers to produce sparse representations compatible with inverted-index retrieval. Experiments on CLEF-IP 2013 show that Sparse Coverage matches or exceeds the document-level recall of strong dense patent encoders in several configurations, while remaining competitive for passage-level retrieval. By combining local semantic evidence with sparse inverted-index search, Sparse Coverage provides an effective first-stage retrieval approach for patent search.

---

### An automatic-differentiation framework for time-lapse electrical resistivity tomography inversion of hydrologic dynamics

Authors: Pu Yang, Zhengyang Fang, Yuxin Liu, Xuan Su, Deshan Feng, Hang Chen
Published: 2026-07-31
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.14661v1

Time-lapse electrical resistivity tomography (TL-ERT) provides spatially distributed information on subsurface hydrologic changes. However, inversion of long monitoring sequences is computationally demanding. Modifying the data misfit, regularization, model parameterization, or petrophysical transformation may also require new gradient derivations and separate implementations. Here, we present AD-TLERT, a unified, GPU-accelerated framework for time-lapse ERT inversion based on automatic differentiation. The framework integrates model parameterization, differentiable petrophysical transformations, forward modeling, data misfit, regularization and auxiliary constraints into a single computational chain. Alternative inversion formulations can therefore reuse the same PDE derivative implementation without re-deriving the complete ERT sensitivity for each case. Comparisons with pyGIMLi showed close agreement in the forward responses, gradients, and recovered resistivity models. Under the tested configuration, AD-TLERT achieved an approximately 51-fold speedup. Synthetic experiments showed that inversion choices affect the amplitude, geometry, and temporal behavior of recovered anomalies. By propagating gradients through the embedded petrophysical relationship, AD-TLERT enabled direct water-content inversion and yielded more accurate estimates than post-inversion conversion for the tested model. A field application further demonstrated how ERT, temperature, and soil-moisture observations can be combined to image snowmelt-driven hillslope wetting. AD-TLERT provides an efficient and flexible framework for time-lapse ERT inversion and hydrologic interpretation.

---

### Ring-based Spatial Transformer: Learning Non-linear Spatial Interactions between Building Distribution and Pedestrian Flow

Authors: Shun Nakayama, Takahiro Kanamori, Wanglin Yan
Published: 2026-07-31
Categories: cs.LG, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2608.14660v1

This study proposes a ring-based SpatialTransformer to learn how building uses at different distances from a railway station interact to generate pedestrian flow. Concentric ring buffers at 100-meter intervals up to 800 meters were defined around 100 randomly selected stations in Tokyo, treating each ring as a spatial token. Self-Attention was applied to learn inter-zone interactions directly from data, without prior structural assumptions. GPS-derived walking trip counts served as the target variable and Geographically Weighted Regression as the baseline. Across 30 independent trials, the SpatialTransformer consistently outperformed GWR in predictive accuracy. SHAP analysis revealed that mid-to-outer distance zone features dominate pedestrian flow prediction, while features from the 0-100m zone contributed little. The attention matrix showed that each distance zone attends most strongly to spatially distant zones, demonstrating that pedestrian flow is regulated by structural interactions across the entire catchment area rather than by any single zone in isolation. These findings challenge the compact city assumption that station-proximate development maximizes pedestrian flow, and suggest that land use distribution across the full walkable catchment area deserves greater consideration in urban planning practice.

---

### When Uncertainty Isn't Enough: An Empirical Study of Self-Correction in Code Generation

Authors: Pranav Rakasi, Maanas Lalwani, Arnav Srivastava, Arya Palanivel, Tinuade Adeleke, Ruizhe Li, Sean Wu
Published: 2026-07-31
Categories: cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2608.14659v1

Large language models for code generation often produce incorrect solutions without reliable indicators of failure. We study whether uncertainty estimation methods developed for natural language transfer to code generation, and whether such signals can improve code generation via selective self-correction. We evaluate five uncertainty methods: mean token entropy, verbalized confidence, $P(\text{True})$, entropy ensembles, and semantic entropy probes, across three small code LLMs on HumanEval and BigCodeBench. We find that multi-sample $P(\text{True})$ achieves the strongest correlation with correctness, while all the other methods, including semantic entropy probes, yield only weak correlation. We then use these uncertainty signals to drive three self-correction policies: adaptive decoding, uncertainty-based regeneration, and verification-based regeneration. Our results reveal a stronger negative finding than anticipated: uncertainty-based self-correction fails to reliably improve Pass@1, degrading accuracy in 5 of 6 configurations across both benchmarks ($-3$pp to $-10$pp), and adaptive decoding degrades accuracy in 4 of 6 configurations. Only verification-based self-correction reliably improves Pass@1, with gains of $+6$ to $+26$ percentage points on HumanEval and $+8$ to $+20$ percentage points on BigCodeBench, scaling inversely with baseline strength. These findings replicate consistently across both benchmarks and suggest that cheap uncertainty estimators are insufficient on their own to improve code correctness, and that their practical value lies in serving as gating signals for costlier execution-based correction loops rather than as standalone substitutes for verification.

---

### pico-type: A 1.5M-Parameter Byte-Level Multi-Head Content Classifier

Authors: Gautam Kishore
Published: 2026-07-31
Categories: cs.LG, cs.AI, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2608.14658v1

We introduce pico-type, a byte-level multi-head content classifier with approximately 1.5 million parameters that simultaneously predicts seven content properties from raw UTF-8 bytes in a single forward pass. Operating directly at the byte level -- no tokenizer, no subword vocabulary, no pretrained embeddings -- pico-type classifies coarse type (12 classes), modality (8), subtype (24), code language (62), text language (30), file MIME type (90), and risk flags (6-label multi-label: API keys, JWTs, passwords, emails, phone numbers, SSH keys). The architecture combines a learned byte embedding, three convolutional blocks with growing receptive fields, two bidirectional attention layers with rotary position encodings, and a statistical pooling layer feeding seven Matryoshka-style classification heads. Four tiered variants (tiny/small/base/pro) share the same trunk with sliced representations from 16 to 576 dimensions, yielding ONNX exports under 210 KB and CPU inference under 10 ms. Trained on a mixture of synthetic templates and real-world data (8709 GitHub code samples, 5000 Wikipedia articles), pico-type achieves 60.3 percent code language accuracy on The Heap benchmark (24 languages) and 98.2 percent text language accuracy on Wikipedia (30 languages) -- improvements of +57 and +79 percentage points respectively over the synthetic-only baseline. Format-based heads (coarse, modality, subtype, file_mime, risk) maintain 100 percent accuracy on synthetic benchmarks. The model, code, and pretrained weights are released under Apache 2.0.

---

### LUNG-KGMM: Knowledge-Guided Multimodal Learning for Lung Cancer Incidence Prediction

Authors: Chunlei Yang, Shuyan Li, Zhong Cao
Published: 2026-07-31
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2608.14657v1

Early identification of lung cancer risk is critical for timely intervention, yet existing prediction models are limited by their reliance on single data modalities and their inability to leverage structured clinical knowledge. We propose LUNG-KGMM, a knowledge-guided multimodal framework that integrates longitudinal electronic health records, radiology reports, chest radiograph representations, and guideline-derived knowledge for 1-to-6-year incident lung cancer prediction. To address modality heterogeneity and potential data leakage, we develop a leakage-sanitized report processing pipeline and a horizon-masked cumulative training objective that handles incomplete follow-up. We further introduce a knowledge-graph representation of clinical guidance that encodes report-triggered finding-attribute-action relations as an auditable knowledge stream. We build a multimodal development cohort from the publicly available MIMIC databases and construct a real-world validation cohort from the Xiamen Medical Big Data Platform. Extensive experiments on the MIMIC cohort demonstrate that LUNG-KGMM achieves superior performance over state-of-the-art methods, and validation on the Xiamen cohort further characterizes its cross-cohort portability and the need for local adaptation. The MIMIC development cohort is publicly accessible; the Xiamen cohort is governed by local data privacy regulations.

---

### P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval

Authors: Zhongli Wu, Zhuangzhi Gao, He Zhao, Feixiang Zhou, Fu Wang, Jinru Ding, Yuankai Wang, Hongyi Qin, Gregory Y. H. Lip, Bil Kirmani, Yalin Zheng
Published: 2026-07-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.14656v1

Photoplethysmography (PPG) is widely used in consumer wearables because of its low cost and ease of acquisition. However, unlike electrocardiography (ECG), PPG measures peripheral pulse dynamics rather than cardiac electrical activity, limiting its ability to predict cardiac conditions that rely on ECG-specific morphological cues. Existing methods attempt to bridge this gap by reconstructing ECG signals from PPG signals. However, this inverse mapping is inherently ill-posed, and faithful waveform reconstruction does not necessarily translate into improved downstream performance. To address this challenge, we propose P2E-VQ, a retrieval-augmented framework that replaces ECG waveform reconstruction with ECG-linked representation retrieval. Specifically, P2E-VQ converts PPG patches into discrete tokens and retrieves ECG-linked information from a memory bank constructed exclusively from the training data. This process augments PPG representations while requiring only PPG signals during inference. Extensive experiments on five public datasets covering six downstream tasks, including clinical endpoint prediction and affective state recognition, demonstrate that P2E-VQ consistently outperforms pretrained baselines under a unified frozen-feature linear-probing protocol.

---

### Diagnosing and Mitigating Perception-Decision Misalignment in Omni-LLMs via Modality Subspace Activation

Authors: Hongbo Jiang, Jie Li, Yunhang Shen, Tianyu Xie, Pingyang Dai
Published: 2026-07-31
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2608.14655v1

Omni-Large Language Models (Omni-LLMs) power complex multi-modal reasoning in applications like World Action Models and autonomous agents. However, their strong performance often masks a profound Perceptual-Decision Misalignment (PDM), where decisions remain unfaithful to multi-modal perceptions. To diagnose this, we formalize Causal Modality Sensitivity (CMS), operationalized via a dual-lens framework: Answer Retention Rate (ARR) at the macro behavioral level, and Logit Angular Discrepancy (LAD) to track microscopic distribution shifts. We also curate CausalMSBench, a diagnostic dataset isolating language priors. Benchmarking reveals that popular Omni-LLMs exhibit critically low CMS, showing negligible distribution shifts even when key modalities are removed. To rectify this, we propose Modality Subspace Activation (MSA), a training-free inference-time framework that uses Singular Value Decomposition (SVD) to estimate modal activation strengths. MSA dynamically balances modal projections in the last hidden state, effectively restoring CMS across benchmarks.

---

### FedImp: Enhancing Federated Learning Convergence with Impurity-Based Weighting

Authors: Hai Anh Tran, Cuong Ta, Truong X. Tran
Published: 2026-07-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.14654v1

Federated Learning (FL) is a collaborative paradigm that enables multiple devices to train a global model while preserving local data privacy. A major challenge in FL is the non-Independent and Identically Distributed (non-IID) nature of data across devices, which hinders training efficiency and slows convergence. To tackle this, we propose Federated Impurity Weighting (FedImp), a novel algorithm that quantifies each device contribution based on the informational content of its local data. These contributions are normalized to compute distinct aggregation weights for the global model update. Extensive experiments on EMNIST and CIFAR-10 datasets show that FedImp significantly improves convergence speed, reducing communication rounds by up to 64.4%, 27.8%, and 66.7% on EMNIST, and 44.2%, 44%, and 25.6% on CIFAR-10 compared to FedAvg, FedProx, and FedAdp, respectively. Under highly imbalanced data distributions, FedImp outperforms all baselines and achieves the highest accuracy. Overall, FedImp offers an effective solution to enhance FL efficiency in non-IID settings.

---

### Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms

Authors: Xianzong Wu, Xiaohong Li, Yuejun Guo, Xinyang Liu, Tianlin Li, Junjie Wang, Qiang Hu
Published: 2026-07-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.14653v1

Prediction uncertainty is a widely adopted metric for quantifying model confidence, with downstream applications spanning model explanation, data selection, and prediction rollback. Despite its demonstrated utility, the potential of uncertainty quantification to enhance code generation in large language models (LLMs) remains largely underexplored, raising a critical question: to what extent can uncertainty serve as an effective signal for improving LLM-based code generation? To answer this question, we study uncertainty-aware rollback decoding, an inference-time strategy that uses uncertainty signals to identify unreliable generation regions and roll back to earlier valid prefixes without retraining the model. We evaluate this framework on seven code LLMs, five code generation benchmarks, and eight token-level uncertainty signals under a unified decoding setup. Our results show that the complete rollback framework improves over equal-budget restart across the evaluated benchmarks and model settings, with gains of up to 0.26 in pass@1 and 0.35 in AvgTestPassRate on functional code generation benchmarks, and an absolute improvement of up to 6.4\% in Patch-Aligned Safe Rate on Dsec-Python. Among the evaluated signals, information-theoretic measures such as token entropy and negative log-likelihood show the most favorable overall trend, frequently achieving the best or near-best results on standard benchmarks. A component-controlled ablation further shows that feedback-guided rollback provides the main improvement, while uncertainty localization provides an additional gain when checking, budget, rollback, and branch decay are held fixed.

---

### Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling

Authors: Yang Zhao, Peisong Niu, Tian Zhou, Ziqing Ma, Guanlong Ma, Rong Jin, Huiling Yuan, Liang Sun
Published: 2026-07-31
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2608.14652v1

The development of 0.1$^{\circ}$ global weather forecasting models based on machine learning (ML) is constrained by the limited availability of high-resolution data, as decades of reanalysis are only available at 0.25$^{\circ}$ resolution. While existing approaches fine-tune 0.25$^{\circ}$ forecast models on limited 0.1$^{\circ}$ samples, we show that this transfer is hindered by the irreversible information loss inherent in coarse-resolution forecasting. Therefore, we propose BaguanHR, a framework that shifts the focus from transferring models to transferring data. We first show that super-resolution (SR) has lower conditional entropy and input amplification than forecasting, making it a more robust vehicle for resolution transfer. By leveraging this advantage through variable-wise SR, we synthesize extensive 0.1$^{\circ}$ data from ERA5. BaguanHR's performance on the synthetic-plus-real dataset exceeds both ML-based methods and IFS-HRES, achieving superior performance across over 85% of the lead times within 72 hours. Furthermore, our findings highlight a power-law scaling effect, as a twofold increase in data reduces RMSE by 4.6% for 72-hour forecasting and 4.9% for 120-hour forecasting. Our results demonstrate that scaling high resolution ML-based forecasting is primarily a data bottleneck, and that variable-wise super-resolution provides a simple yet general solution to unlock long coarse-resolution reanalyses for high-resolution training.

---

### Measuring Cross-Task Behavioral Consistency in Language Model Agents

Authors: Amritesh Banerjee, Pranil Raichura
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.13598v2

Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether an agent succeeds but not how consistently it behaves. We argue that behavioral consistency across tasks is a distinct and measurable property, and we introduce the Behavioral Consistency Metric (BCM) to quantify it. BCM trains a model to predict task success from behavioral features of agent execution traces, derives a per-trajectory feature-attribution vector, and measures the mean pairwise similarity of these vectors within an agent system. Across roughly 9,000 trajectories from six language model agents on software engineering tasks, our central finding is that cross-task and within-task consistency are distinct axes that can diverge: some systems are locally reproducible, behaving similarly on repeated attempts at one task, yet globally fragmented, with no stable strategy across different tasks, while others are consistent at both scales. Prior work measures only same-task reproducibility and so cannot observe this separation. We further find that consistency is not reducible to success rate, since systems with comparable success can differ sharply in consistency, and that the frontier-versus-open-source consistency gap persists under a within-task control that holds task difficulty constant. We position BCM as a process-level reliability signal that complements outcome metrics, and we are explicit about the conditions under which it is meaningful.

---

### Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography with Diffusion Models

Authors: Hongxin Xu, Jianping Mei, Can Wang, Defang Chen
Published: 2026-07-31
Categories: eess.IV, cs.AI, cs.CR, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2608.13597v1

Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image from the stego. Existing diffusion-based CIS methods can generate natural-looking stego images but preserve substantial visual similarity to the secret image. This resemblance risks exposing structural and semantic cues, giving rise to security vulnerabilities that cannot be evaluated solely via recovery fidelity. Achieving substantial visual dissimilarity between the secret and stego images without compromising stego quality and recovery fidelity remains challenging. To address this issue, we propose InvCISD, an invertible diffusion framework that couples the latent representations of the secret and an irrelevant reference image with an invertible network called LIMNet. We first train LIMNet in diffusion latent space, followed by end-to-end fine-tuning of the entire network, i.e., LIMNet integrated diffusion inversion and generation modules. Experiments demonstrate that the proposed method substantially reduces secret-stego visual similarity, improves stego quality, and retains satisfactory secret reconstruction quality. Our further investigation shows that all evaluated methods are highly detectable by the CIS-oriented steganalysis model, indicating that resistance against targeted steganalysis constitutes a critical direction for future CIS research.

---

### Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning

Authors: Jiahe Fan, Si Chen, Yinghao Hou, Aiyuan Zhang, Hong Xie
Published: 2026-07-31
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2608.13596v1

Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-scale setting: improving a small recipient language model with a stronger donor despite substantial architectural mismatch. We ask whether useful capabilities can be transferred without explicit neuron-wise semantic alignment. Building on the observation that truncating a large model to a smaller architecture and injecting it with a tiny mixing weight can already improve the recipient, we propose Activation-Prune-Merge (APM), an activation-guided framework for cross-scale fusion. APM constructs task-conditioned activation maps on the donor, selects salient layers, hidden dimensions, attention heads, and MLP neurons to prune it to the recipient architecture, and injects the resulting donor slice into the original recipient using a micro interpolation coefficient. This formulation treats the donor as a source of concentrated functional components rather than requiring precise structural transplantation. Across 16 benchmarks spanning reasoning, mathematics, code generation, instruction following, and classification, APM improves the overall average accuracy from 55.5% to 60.6% over the original 3B recipient. RTE accuracy increases from 64.3% to 82.3%, QNLI from 52.3% to 65.7%, and BoolQ from 70.8% to 79.2%. Analyses of injection ratios and sequential multi-stage fusion further suggest that activation-guided extraction improves the quality of the transferable donor slice while preserving the small-ratio fusion regime. These results provide evidence that cross-scale heterogeneous fusion can succeed without explicit semantic alignment when the donor contribution is sufficiently concentrated and carefully selected.

---

### Decode-Branch Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation

Authors: Liming Liu, Mingze Wang, Tuo Zhao
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.12385v3

As large language models serve ever more requests, cumulative inference cost is growing relative to the one-time cost of training. In typical serving, prompt prefill runs in parallel and is compute-bound, whereas autoregressive decode is sequential and memory-traffic-bound. Conventional width or depth scaling raises both costs together, since every added layer is evaluated in both phases and enlarges the weights read at each decode step. We instead ask whether additional learned computation can be allocated to continuation prediction while preserving prompt-wide primary computation and a single KV cache. We realize this with the Decode-Branch Transformer. Its primary path alone processes the prompt and writes the KV cache; the decode branch is omitted during prefill and activated only from the final prompt position onward, adding continuation computation without writing state or affecting the primary path. The paths share attention, MLP, and output matrices, using separate token embeddings with lightweight coupling. Grouped decode reuses loaded weight tiles and the primary KV cache across both paths, so the added arithmetic does not proportionally increase dominant memory traffic or decode latency. Across matched-token comparisons, Decode-Branch achieves lower validation loss across architectures and data settings. In MoE models, the primary and branch expert fan-outs become independent knobs for trading prompt cost, decode cost, and predictive quality. We study two expert-allocation regimes, holding prefill or decode computation fixed, and expose a prefill-decode-quality trade-off enabled by phase-specific expert allocation.

---

### Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction

Authors: Zhiqi Wang, Yichi Zhang, Dongwon Lee, Yuchen Yang
Published: 2026-07-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.11242v1

When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of user-issued instructions, Session Constraints (SCs), such as "do not delete any emails until I confirm," that are meant to constrain LLM's behavior for the remainder of a session but are silently dropped during compaction. To quantify this loss, we introduce COMPINT, an evaluation suite that evaluates compactors across three long-context scenarios: multi-turn chat, agentic trajectory, and long-horizon research. Current compactors retain only 17% of injected SCs on average, and most perform worse than running the same task without compaction. Retention varies sharply with compactor, prompt, context length, SC phrasing, and injection location, showing that the loss is systematic rather than tied to any single setting. We propose an SC-aware extractor that runs alongside the compactor as a plug-and-play module, achieving over 90% retention across all three scenarios without modifying the compactor or LLM. The COMPINT evaluation suite and accompanying implementation are available at https://github.com/ZhiqiEliWang/compaction-integrity.

---

### RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle

Authors: Dongyang Ao, Kaixiang Fang, Shijie Xu
Published: 2026-07-31
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2608.11241v1

Deploying LLM agents into industrial recommender operations exposes a three-way tension we frame as the autonomy-determinism-efficiency trilemma: general autonomy (interpreting operator intent, generating glue code zero-shot), industrial determinism (schema-conforming feature extraction, non-crashing A/B, zero compliance-path hallucination), and end-to-end efficiency. Any two can be maximized against the third. We present RecSys Factory, an LLM-agent platform deployed for 78 days across three heterogeneous Tencent recommender business lines. The design principle is autonomy at decision points, not over pipelines, made concrete through three deconstructions that each discharge one vertex of the trilemma. Runtime is deconstructed into three host-emitted event sources (Claude Code Stop hooks, corporate-IM webhooks, workflow scheduler APIs): the platform carries no long-running daemon during the wait phase and consumes zero CPU during the 94% of wall-clock spent waiting on Spark or GPU jobs. Capability is deconstructed into a 29-file skill ecosystem (8,971 lines of SKILL.md) whose per-skill pitfall tables mechanically compile into a 400-entry PitfallStore, confining autonomy to bounded typed decision surfaces inside pre-committed pipelines. Deployment spans three business lines with disjoint label semantics, A/B layer topologies, and operator personas; an onboarding-time compression is observed on two of the three and is reported as a case-study observation, not a generalization claim, and not measured against a controlled pre-platform baseline. The human is retained at the diagnostic-versus-execution boundary via a human-in-the-loop card protocol, deployed as an audit-trail primitive (schema-validated, idempotent, replayable) and reported from an 8-day 16-run pilot. Across the 78-day window the platform recorded 1,624 CLI-tool dispatches at a 78.6% aggregate success rate.

---

### VQ-bench: A Composable Vector Quantization Framework

Authors: Ashwin Padaki, Amir Ingber, Edo Liberty
Published: 2026-07-31
Categories: cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2608.11240v1

Vector quantization is an old problem but has recently become central to AI infrastructure. It is therefore experiencing a surge of renewed engineering and research activity. This paper provides a unified framework for developing and benchmarking new quantization algorithms. We describe 7 common conceptual quantization primitives and show how to compose them arbitrarily. We then re-express 25 common quantizers as pipelines of these primitives. Finally, we publish VQ-bench as open-source to be extended further and make reproducible benchmarks publicly available.

---

### Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization

Authors: Yifan Wang, Patrick Royer, Raphaël Féraud, David Delande
Published: 2026-07-31
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2608.11239v1

Administering Database Management Systems (DBMS) instances requires Database Administrators (DBA) to balance performance in terms of Service Level Agreement (SLA) against resource usage, often prompting RAM over-allocation that wastes memory. We introduce MicroTune, an online RL-based buffer adjustment system that minimizes unnecessary memory allocation while ensuring SLA compliance. To identify the most effective RL core, we evaluate multiple algorithms under diverse benchmark workloads, training MicroTune on extensive traces of both external metrics (latency, throughput) and internal DBMS metrics (status variables and performance statistics). Experimental results demonstrate that MicroTune dynamically adapts buffer sizes to workload fluctuations, outperforming baselines by achieving significant memory savings with fewer SLA violations. These findings underscore the promise of reinforcement learning for adaptive resource management in DBMS environments.

---

### Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability

Authors: Jeonghwan Choi, Taewon Yun, Minjeong Ban, Gyeonghun Sun, Jae-Gil Lee, Hwanjun Song
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.11238v3

Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence, yet existing evaluation frameworks struggle to provide consistent, fine-grained diagnostics across the diverse spectrum of user queries, ranging from close-ended fact-seeking to open-ended explanatory requests. We propose Q-CARE, a query-agnostic and fully reference-free framework that enables fine-grained assessment by decomposing queries into sub-queries and answers into atomic claims. Q-CARE establishes a unified evaluation principle based on query coverage and claim verifiability, yielding coverage-aware retriever metrics (C-Prec@k, C-nDCG@k) and claim-level generator metrics (Completeness, Conciseness, and Verifiableness). On a human-annotated benchmark spanning eight datasets, Q-CARE achieves higher correlation with human judgments than four existing RAG evaluation metrics, including RAGEval and RAGChecker, proving its effectiveness as a reliable, automated evaluation framework. Code and data are publicly available at https://github.com/DISL-Lab/Q-CaRE-COLM-26.

---

### Geometry-aware Incremental Neural Operator for Long-Horizon PDE prediction

Authors: Jiaquan Zhang, Shuxu Chen, Haifan Meng, Yi Lu, Zhihan Lyu, Fan Mo, Wei Dong, Yang Yang, Chaoning Zhang
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.11237v1

Neural operators have shown strong potential for learning solution operators of partial differential equations (PDEs). However, long-horizon autoregressive prediction remains challenging: local errors accumulate as spectral inconsistency, phase misalignment, or mean drift. Existing methods mainly improve state representations and operator backbones, while leaving the repeatedly applied latent transition increment weakly structured, allowing spectral errors and unstable channel couplings to accumulate during rollout. To address these issues, we propose a geometry-aware incremental neural operator (GeoIncNO) for stable long-horizon PDE prediction. GeoIncNO predicts latent increments for residual advancement and uses lightweight low-rank projectors to regulate channel coupling within active frequency bands derived from the increment spectral energy distribution. To reduce physical-space reconstruction errors, GeoIncNO further introduces a mean--fluctuation decoupled reconstruction mechanism, where stable mean structures and dynamic fluctuations are fused separately, and phase correction is applied only to the zero-mean fluctuation component. Extensive experiments on six PDE benchmarks, covering 1D, 2D, and 3D dynamical systems, show that GeoIncNO achieves consistently strong prediction accuracy, improved rollout stability, and better spectral fidelity compared with competitive neural-operator baselines.

---

### TRACE Bench: Task-driven Roleplay Agentic Checklist Evaluation

Authors: Jiahui Zhang, Ziwei Zhang, Yipeng Wang, Yibo Liu, Haozhou Pang, Yikai Hu, Hongyan Ren, Lan Zhou, Qi Gan, Kai Sheng
Published: 2026-07-31
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.11236v1

Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and which dialogue evidence supports the judgment. We propose TRACE Bench, a task-driven agentic checklist evaluation framework. It decomposes each role profile offline into a fixed checklist, then uses a User Agent to converse naturally with the target roleplay model while privately updating checklist states from model responses. Scores therefore trace back to checklist items and supporting dialogue turns rather than a black-box holistic impression. For coverage cross-validation, we audit released M2 free-dialogue transcripts from the MiniMax Role-play Benchmark against the same role-derived checklist. The released free-chat transcripts cover only 73.74% of key role-profile points, whereas TRACE Bench reaches 99.91% coverage in fewer turns. Robustness experiments show stable rankings under repeated runs and User Agent replacement. Across 26 models, TRACE Bench reports overall rankings together with capability breakdowns and checklist traces. It also supports Closed-Loop Benchmark Evolution, distilling verification methods proven effective in failed traces so later evaluations can more reliably elicit and examine observed failure modes.

---

### CORA-Diff: Confidence-Oriented Residual Acceptance for Efficient Diffusion Language Model Inference

Authors: Yifan Wu, Yufeng Zhang, Kenli Li
Published: 2026-07-31
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.11235v1

Diffusion language models (DLMs) update many tokens in parallel, yet practical decoders often use a fixed denoising horizon. Many predictions stabilize early, but blockwise decoding continues until all positions are resolved, causing repeated dense forward passes. Existing accelerators often rely on learned filters, modified scores, dependency models, or cache-specific mechanisms. We ask whether native trajectory signals can identify residual positions likely to match the deterministic dense endpoint. We propose CORA-Diff, a training-free method that preserves the original transfer rule and applies confidence-and-persistence gating only to positions that rule leaves unresolved. Accepted tokens remain visible as context, and the block terminates once all positions are resolved. This requires no backbone change, learned acceptance model, or logit modification. Our theory explains why high-confidence, persistent predictions are more likely to match the fixed-horizon dense endpoint, and paired post-intervention trajectories provide direct empirical support. We select one operating point on a separate GSM8K calibration subset and freeze it for all evaluations. Under a matched Learn2PD-style LLaDA protocol, CORA-Diff has the lowest measured runtime in all eight task-length settings. Task scores match or exceed dense decoding in five settings, and the largest observed drop is 1.22 points. Its incremental speedups over EOS-aware dense decoding are 2.70x and 3.32x on GSM8K and HumanEval. It also reaches 13.14x under the fixed-horizon 1024/1024 mechanism-isolation protocol and transfers to Dream without retuning at 3.18x-3.53x. These results show that native confidence and persistence enable reliable residual acceptance, reducing repeated denoising computation while preserving task quality.

---

### InfraBench: Evaluating Infrastructure Agents Across Layers, Lifecycle, and Risk

Authors: Yuan Gao, Zeren Yang, Junnan Li, Shawn, Zhong, Ahmed Dajani, Mai Zheng, Andrea Arpaci-Dusseau, Remzi Arpaci-Dusseau
Published: 2026-07-31
Categories: cs.AI, cs.OS
arXiv: https://arxiv.org/abs/2608.11234v3

Managing modern computing infrastructure has become a steadily harder problem due to the ever-increasing complexity. Recent advances in AI agents create a timely opportunity to automate infrastructure management tasks, but it remains unclear how well such agents can handle real-world infrastructure complexity. We present InfraBench, a benchmark suite for evaluating AI agents on realistic infrastructure tasks across the full system stack and full operational lifecycle with fine-grained risk assessment. Experiments with 15 agent-model configurations show that even the strongest agent cannot secure a full score across all tasks. Mean effective scores range from roughly 40% to 88% (with per-configuration standard errors of 6-12 points), repeating every task three times reveals that top configurations still pass only a fraction of their attempts, and per-check scoring exposes a general failure pattern: agents may routinely satisfy short-term objectives while leaving non-durable changes, broken distributed invariants, unsafe side effects, and uncleaned state behind. INFRABENCH, including its live leaderboard, tasks, and evaluation harness, is publicly available at infraben.ch.

---

### Retrofitting Recurrent Depth into a Pretrained Language Model: Installation, Extrapolation, Transfer, and Retention at Two Parameter Budgets

Authors: Mark Shapiro
Published: 2026-07-31
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.11233v1

A dense, pretrained language model can be retrofitted with recurrent depth and learn an iterative latent transition that persists after outcome-only annealing. Qwen2.5-0.5B-Instruct is split into a Prelude, a weight-tied Recurrent Block, and a Coda, with an identity-preserving one-loop path and a re-entry bridge on later loops. At loop 1 the retrofit remains non-inferior to its base on a preregistered ARC battery. Three findings. First, the mechanism is a reusable procedure rather than terminal-answer lookup, and installs at two budgets: 6M trained parameters over frozen base weights and 180M full-block. With intermediate-step supervision, the model computes one task step per loop and persists when only final answers are graded. The adapter matched the full block overall (83.8% versus 84.0%), led through depth 11, and trailed beyond. Verbal fine-tuning reached 79-86% on controlled verbal renderings (zero-shot transfer was minimal), and adapter verbal training begun from the installed mechanism outpaced matched fresh training by 18.6 points, including on a held-out test set. Second, the operation extrapolates to roughly 1.5 times its supervised depth, holding 70% accuracy through depth 18. Third, a same-size scratchpad-trained model matched the recurrent model within its learned horizon but collapsed beyond it. The recurrent model won overall, 84% versus 72%, retained 53% versus 2.5% beyond depth 10, and answered 7.6 times faster. An iterative transformer can therefore perform deeper reasoning in latent space faster than comparable or larger models fine-tuned on the same task, in a system-level comparison. A second task, running the rule in reverse, exposed the limits: the inverse was learnable in isolation, but no continuation acquired it while preserving the installed mechanism and general capability, a catastrophic-interference boundary. Learned depth selection remains open.

---