# Research Papers — 2026-08 · bundle page 230 of 240 > Full-text markdown of papers #11451–11500 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/230 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/229.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/231.md) ### DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial Authors: Abay Zhurekbay, Tao Liu, Fan Li Published: 2026-08-02 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.02678v1 Retrieval-augmented generation (RAG) systems are vulnerable to corpus poisoning: an attacker who inserts a crafted document into the retrieval corpus can steer the underlying large language model (LLM) toward an attacker-chosen wrong answer. Prior single-document attacks typically avoid explicitly naming and refuting the correct answer inside the poisoned passage. In this paper, we examine a complementary design and propose \emph{DenialRAG}, a single-document poisoning attack that explicitly names the correct answer, denies it, and presents an attacker-controlled explanation for favoring the wrong answer. By placing both the correct answer and the corresponding poisoned answer inside the same retrieved passage, DenialRAG embeds the conflict directly into the context seen by the generator. We evaluate DenialRAG against four published single-document poisoning attacks across three open-domain question-answering datasets, eight target LLMs from four vendors, and five inference-time defenses. The results show that attack effectiveness is strongly model-dependent: DenialRAG achieves the highest attack success rate (ASR) on all three Mistral-7B datasets and remains effective on several other target LLMs, while other attacks dominate in some model regimes. Defense results show meaningful ASR reductions but non-uniform protection, with each defense leaving residual ASR in some settings. Component-level and cross-model analyses further identify the embedded denial as the most influential tested component and show that different poisoning mechanisms lose effectiveness at different rates across model groups. Together, these results show that RAG poisoning risk cannot be fully characterized by a single attack family or a single target model. --- ### When Policies Change Probabilities: Modular Decision-Making for LLM Code Review Authors: Rasvik Kudum, Max Corbett, Hitansh Paliwal, Romaisa Fatima, Thomas Jiralerspong, Sneheel Sarangi Published: 2026-08-02 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.02677v1 LLM code reviewers often estimate patch risk and make approval decisions in one prompt. A probability should depend on evidence; costs should determine the action taken from it. We test whether four deployed reviewer interfaces preserve this separation using 15,792 responses on 720 candidate patches, with one that passed and one that failed an archived test harness for each of 360 repository issues. In matched calls with the patch and monitor evidence fixed, replacing an equal-cost policy with a 10:1 false-accept policy changes reported failure probabilities by 13.6 to 16.9 percentage points on average. For every reviewer, the actions returned under the high-cost prompt are worse than rejecting all patches. Applying the same high-cost rule to probabilities elicited under equal costs reduces loss for all four systems, showing that probability elicitation itself contributes to the excess loss. We also evaluate a modular pipeline that elicits risk without policy information, combines an independent monitor score, and applies costs in code. Relative to calibrated reviewer-only scores, the pipeline improves average probability accuracy and, at equal costs, reduces mean loss by .073 per issue while accepting 58 to 68% of patches. At 10:1, it accepts none and matches reject-all. Downstream policy can therefore change the probability it is meant to use, motivating separate evaluation of risk, outside evidence, and action. --- ### Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks Authors: Shangze Li, Chuancheng Shi, Simiao Xie, Lingzhi He, Cheng Ji, Zifeng Cheng, Fei Shen, Chao Wu, Tat-Seng Chua Published: 2026-08-02 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.02674v1 With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly identify and disrupt internal safety neurons or routes. However, existing safety defenses often rely on static safety units or fixed refusal pathways, leaving models highly vulnerable to targeted route-level white-box attacks. For that, we propose dynamic routing adaptive alignment (DRAA), a framework that introduces dynamic compensatory routes to preserve robust refusal behavior when the safety route is compromised. Specifically, we first identify and localize the model's safety route by contrasting internal activations between safe and unsafe calibration samples. DRAA then masks this safety route to induce causal failure cases and selectively mines the resulting defense failures, thereby constructing failure-aware preference pairs. Extensive experiments demonstrate that DRAA effectively restructures the underlying pathway dependence of model safety, substantially improving robustness against route-level white-box attacks, while preserving general utility. --- ### dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model Authors: Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Yiwei Guo, Colin Zhang, Shuai Wang, Kai Yu Published: 2026-08-02 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2608.02673v3 Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a precise and explicit interface for speech editing: a transcript-grounded structural edit instruction with XML-style tags explicitly specifies typed operations and localizes them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots$.$tts$.$edit, an editor adapted from the continuous autoregressive dots$.$tts foundation model. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual evaluation suite that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity. --- ### dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model Authors: Hankun Wang, Bohan Li, Shi Lian, Xiaoyu Gu, Jing Peng, Da Zheng, Colin Zhang, Kai Yu Published: 2026-08-02 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2608.02673v1 Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a precise and explicit interface for speech editing: a transcript-grounded structural edit instruction with XML-style tags explicitly specifies typed operations and localizes them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides an externally inspectable contract for compositional edits. We instantiate the interface in dots.tts.edit, an editor adapted from the continuous autoregressive dots.tts foundation model. Four representative speech-creation controls cover lexical content, affective expression, pitch and speaking-rate delivery, and temporal phrasing through text, emotion, prosody, and pause editing. Task-specific data pipelines construct operation- and scope-controlled pairs while retaining source-derived context outside each target region. We further introduce doteBench, a bilingual evaluation suite that measures precise instruction following, local preservation, and audio quality across the four controls and their composition. Experiments show leading overall instruction following and local preservation across its five editing categories, while audio quality remains comparable to existing open-source systems. Across three Seed-TTS-Eval shards, the model shows negligible differences from the base model in zero-shot TTS recognition error rate and speaker similarity. The code and model will be released soon. --- ### Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation Authors: Francis Luis Santos Vargas, Rodrigo Brandão Mansilha, Diego Kreutz Published: 2026-08-02 Categories: cs.CR, cs.AI, cs.ET, cs.SE arXiv: https://arxiv.org/abs/2608.02672v1 Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code is an open question. We benchmark seven models, three closed LLMs (Claude Opus 4, GPT-5.4, Gemini 2.5 Pro) and four open SLMs (Qwen2.5-Coder-14B, WizardCoder-33B, CodeLlama-13B, Magicoder-S-CL-7B), on AWS Terraform generation across 17 scenarios, integrating Checkov and Trivy scanners into a GitLab CI/CD pipeline and evaluating two prompt strategies at three security levels (pass@5). Syntactic validity and security compliance are largely orthogonal properties in LLM-generated IaC, a model that reliably produces well-formed Terraform does not necessarily produce secure Terraform: WizardCoder-33B achieves 77.8% validate rate yet zero Checkov compliance, while Claude Opus 4 reaches 23.1% Checkov and 92.5% Trivy pass rates under detailed security prompting. Consequently, prompt engineering alone is insufficient: automated multi-tool scanning remains a necessary complement to LLM-assisted IaC generation regardless of model family or prompt strategy. All artifacts are publicly available. --- ### On the Performance of Malware Detection Classifiers Using Hardware Performance Counters Authors: Alireza Abolhasani Zeraatkar, Parnian Shabani Kamran, Inderpreet Kaur, Nagabindu Ramu, Tyler Sheaves, Hussain Al-Asaad Published: 2026-08-02 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.02671v1 Malware detection using Hardware Performance Counters (HPC) has emerged as a promising solution to improve the security of computing systems as a complement to antivirus software. Hardware-based malware detectors (HMD) use Machine Learning (ML) classifiers to detect malicious application patterns. The inputs to ML classifiers are low-level performance features known as HPCs, hardware-related activity data collected from a processor at run time to profile the low-level microarchitectural behavior of an application. This paper proposes malware detection using HPCs and machine learning classifiers and highlights the effectiveness of malware detection at run-time. We use ensemble learning techniques to improve the performance of the hardware-based malware detectors, which reduces the number of necessary micro-architectural events. This improves the processor's efficiency by eliminating the need to run an application several times since a processor can measure only 2 to 8 events at a cycle. We use 18 machine-learning models along with two ensemble learning methods to evaluate the malware detection performance, creating a total of 144 different configurations. The experimental results show that the ensemble learning-based malware detection with 2 HPCs using the ensemble technique outperforms standard classifiers with 8 HPCs by up to 10%. It also matches the performance of standard ML-based detectors that use 16 HPCs while requiring only 4 HPCs, thereby enabling effective run-time malware detection. --- ### Permission Denied: Policy-Graded Evaluation of Coding Agents in Hardened Environments Authors: Dotan Davidovich, Yair Amar, Hai Rozencwajg, Or Hiltch Published: 2026-08-02 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.02670v1 Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losses reach 18.3 points and cost inflation 167.3\%, and the two axes disagree; the model that best preserves success is also the one that loses the most efficiency, so model choice is policy-dependent. Beyond aggregate scores, we characterize how agents behave when policy blocks their actions and decompose the failures hardening induces: runs grind into timeouts or wrong solutions rather than stopping early, in a mix that differs by model. To ground comparisons, we verify task solvability under the strictest policy, separating model failures from tasks the policy forecloses. We release Boundary-Bench, an open-source hardening plugin enabling policy-constrained evaluation of coding agents on Terminal-Bench and compatible benchmarks. --- ### Vulnerabilities, Secrets and Misconfiguration in the Highest-Exposure Docker Hub Images Authors: Cristhian Kapelinski, Beatriz Machado, Diego Kreutz Published: 2026-08-02 Categories: cs.CR, cs.AI, cs.CY, cs.OS, cs.SE arXiv: https://arxiv.org/abs/2608.02669v1 Docker Hub is the registry underneath most container deployments, and a flaw in a widely reused base image is inherited by every image built on it. Prior ecosystem-scale measurements each rely on a single detector, leaving the tool-dependence of their counts unquantified, while the studies that do compare scanners use samples of tens to hundreds of images. We present ChimangoScan, a pipeline that crawls the Docker Hub namespace (12,716,568 repositories, 663.8 billion cumulative pulls), reconstructs the image layer graph (54.4 million IS_BASE_OF edges), ranks images by an exposure score that folds an image's own pull count and those of its entire downstream subtree into one scalar, and scans the 52,895 highest-exposure repositories (84.7% of all recorded pulls) with six independent scanners, yielding 170.4 million findings. Vulnerabilities are near-universal: 96.3% of images carry a known package vulnerability, 93.4% a critical one, and 98.0% at least one CIS Docker Benchmark misconfiguration. The posture a single tool reports is largely an artifact of that tool: of 80.7 million distinct (vulnerability, package) groups, 66.8% are flagged by only one of the three vulnerability scanners and just 2.7% by all three, and the best single scanner recovers 66.9%. TruffleHog flags a secret in 76.9% of images, yet hand-labeling 1,100 random detections finds 99.7% are non-credentials. A single zlib CVE reaches images carrying 47.3% of total corpus exposure and propagates to 1.13 million distinct downstream images, but exposure does not predict how vulnerable an image is. We release the pipeline and the 283 GB dataset. --- ### Sphere Retraction Normalizations Authors: Jie Zhang, Cheng-Fang Su, Yi-Jui Huang, Min-Te Sun Published: 2026-08-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.02668v1 Residual connections are the de facto mechanism for training deep neural networks stably. Geodesic Normalization (GeoNorm) recasts them on a Riemannian manifold, orthogonalizing each layer output against the current hidden state and applying the resulting update through the Riemannian exponential map. Every hidden state thus keeps a constant $\ell_{2}$-norm, confining the residual stream to a hypersphere. The exponential map, however, is only one member of a broad family of retraction maps. We show that on the hypersphere this entire family collapses to a single scalar design choice. What distinguishes one retraction from another is only how the magnitude of an update is converted into a rotation angle within the plane spanned by the hidden state and the update. This view places Euclidean residual connections and GeoNorm in one framework. Instantiating it with the metric projection retraction and the Cayley retraction yields Proj-SpheretNorm and Cay-SpheretNorm, which are exactly norm-preserving yet require only algebraic operations. Both prove to be members of a one-parameter family of angular retractions, $p$-SpheretNorm, whose rotation angle saturates rather than growing without bound. The two methods above are recovered exactly at $p = 1$ and $p = 2$, while the identity map and GeoNorm arise only as limits at either end. On nanoGPT, all three methods outperform existing lightweight deep connection schemes, and the best validation loss is attained at finite $p$, indicating that the exponential map is not the preferred retraction for spherical residual streams but merely one end of a spectrum. --- ### Dominant Arm Identification with Mixing and Recycling Observed Samples Authors: Jonghyun Sim, Wonyoung Kim Published: 2026-08-02 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.01545v1 We study the problem of identifying the dominant arm in multi-armed bandits, where the objective is to find the action with the highest probability of exceeding the realized rewards of all other actions. Conventional mean-based and pairwise comparison-based algorithms often fail to identify the arm with the highest realized reward. To address this challenge, we introduce a novel dominant arm criterion and an efficient estimator with theoretical guarantees. Our approach relies on two key technical innovations: (i) a dominance score criterion that an arm beats the locally dominant over the partitioned reward space and (ii) a joint mixing and recycling mechanism coupled with a doubly robust estimator that guarantees simultaneous convergence of the empirical distribution functions for all arms. These key innovations pave a way to efficient computation of global arm dominance. Our proposed elimination algorithm identifies the best dominant arm with nearly optimal rate of sample complexity. Numerical experiments demonstrate that our algorithm consistently achieves exact recovery of the true dominant arm, outperforming existing baselines. --- ### Measuring Product Quality Using Images: The CLIP Q-Score and an Application to Real Estate Authors: Fabian Slonimczyk, Danila Karapsin Published: 2026-08-02 Categories: econ.EM, cs.CV arXiv: https://arxiv.org/abs/2608.01544v1 The CLIP Q-score is a novel, safe, fully reproducible, and computationally efficient method for extracting objective product quality metrics from visual data using contrastive language-image pre-training. We introduce the technique and provide an extensive application to real estate data from an online platform ($\sim500,000$ images). Our open-source metric aligns with LLM assessments and proves to be a powerful predictor of housing market prices for both sales and rentals. We also show that a higher CLIP Q-store is associated with better liquidity (reduced time on the market), especially for properties on sale. --- ### V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memory Authors: Dingyi Kang, Dongming Jiang, Yi Li, Guanpeng Li, Bingzhe Li Published: 2026-08-02 Categories: cs.AI, cs.CL, cs.CV, cs.IR arXiv: https://arxiv.org/abs/2608.01543v1 Interaction between users and LLM agents is increasingly multimodal: conversations interleave text with images, and a later question may target either. Yet most agent memories are designed around text, and even the few that support multimodal conversations still fail on vision-related questions. We trace this failure to an assumption behind the similarity search they rely on: in the index space, a query lies close to the relevant evidence that answers it. In multimodal settings, two gaps break it. By the modality gap, a query lies closer to memory content of its own modality than to evidence in another, even in a trained joint embedding space. By the similarity-relevance gap, the content most similar to a query is often not the evidence that answers it, most acutely when a query carries both text and image and its evidence resembles neither part alone. We present V-Mem, a multimodal agentic memory system that routes retrieval by the modality of the query and that of the target evidence, both recognized from the query alone. To cross the modality gap, V-Mem organizes the conversation into rounds and returns the target-modality content from the same round as the match, without comparing across modalities. To close the similarity-relevance gap, it searches with an LLM-generated anchor that sits closer to the relevant evidence than the query does: a hypothetical caption for a text-only query seeking an image, and an enriched search anchor, the query text plus relevant keywords extracted from the query image, when the evidence is reachable only by combining the two. On Mem-Gallery, V-Mem reaches an LLM-judge score of 0.82 versus 0.56 for the second best, with the largest margin on questions carrying an image (0.87, no baseline above 0.47); on LoCoMo it scores 0.69 versus 0.58. --- ### Celty: SpMSpV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference Authors: Ruokai Yin, Priyadarshini Panda Published: 2026-08-02 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2608.01536v2 Large Language Models (LLMs) increasingly rely on sparsity to cut inference cost, but most prior work exploits a single sparsity source and targets batched multi-user inference. Dual-sparsity, which pairs unstructured weight pruning with runtime activation sparsity, offers a compelling size-accuracy-latency tradeoff for single-user decoding, but forms a Sparse Matrix-Sparse Vector (SpMSpV) workload that existing GPU kernels handle poorly. We propose Celty, a co-designed sparse format, GPU kernel, and SIMT microarchitecture for SpMSpV in LLM inference. Celty's Run-Length Compressed CSC (RLC-CSC) format enables vectorized loading of compressed weight columns and exploits both sparsity sources to skip memory accesses, accumulating partial products in shared memory. The Celty Sparse SIMT Core then adds a pipelined RLC decoder that removes software index reconstruction and repurposes local register files for conflict-free accumulation, operating on the same compressed representation. The kernel alone achieves up to 2.8x over cuBLAS; with the Sparse SIMT Core, speedup reaches 5.3x over cuBLAS at 70% dual-sparsity. --- ### Celty: SpMspV GPU Kernel and SIMT Co-Design for Efficient Dual-Sparse LLM Inference Authors: Ruokai Yin, Priyadarshini Panda Published: 2026-08-02 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2608.01536v1 Large Language Models (LLMs) increasingly rely on sparsity to reduce inference cost, but most prior work targets a single sparsity source-either weight or activation-and optimizes for batched multi-user inference. Dual-sparsity, which combines unstructured weight pruning with runtime activation sparsity, offers a compelling tradeoff among model size, accuracy, and latency for single-user decoding, but formulates as a Sparse Matrix-Sparse Vector (spMspV) workload that existing GPU kernels handle poorly. We propose Celty, a co-designed sparse format, GPU kernel, and SIMT microarchitecture for efficient spMspV in LLM inference. At the kernel level, Celty introduces a Run-Length Compressed CSC (RLC-CSC) format that enables vectorized loading of compressed weight columns and exploits both sparsity sources to skip unnecessary memory accesses, with shared memory used for scattered partial-product accumulation. At the microarchitecture level, the Celty Sparse SIMT Core integrates a pipelined RLC decoder to eliminate software-level index reconstruction and repurposes local register files for conflict-free accumulation-operating directly on the same RLC-CSC format without data layout changes. The Celty GPU kernel achieves up to 2.8x speedup over cuBLAS and 2.4x over Flash-LLM. With the Sparse SIMT Core, speedups reach up to 5.3x over cuBLAS at 70% dual-sparsity. --- ### STAR-VLM: Spatiotemporal Grounding Vision-Language Models for Motion and Velocity Estimation via Automotive Radar Supervision Authors: Pou-Chun Kung, Aryaman Rao, Utkrisht Sahai, Hemanth Murali, Yi Liu, Rui-Yu Lin, Katherine A. Skinner Published: 2026-08-02 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.01535v1 Vision-language models (VLMs) are emerging as a key component of embodied intelligence, with growing applications in auto-labeling and end-to-end autonomous driving. However, existing approaches for improving spatiotemporal reasoning in VLMs often rely on complex preprocessing pipelines, expensive human annotations, or synthetic data, which limit scalability and introduce potential sim-to-real gaps. Moreover, although these methods have improved spatiotemporal understanding, they still lack strong metric reasoning capabilities for dynamic scenes, such as estimating object motion in real-world units. Prior work has explored LiDAR-based metric depth supervision to enhance spatial perception, but it does not directly address temporal reasoning. We introduce STAR-VLM, an automotive radar-supervised framework that enhances spatiotemporal VLMs with motion reasoning and metric velocity estimation for autonomous driving. Automotive radar is a low-cost and widely deployed sensor that provides complementary spatiotemporal supervision through range and Doppler measurements. By leveraging these measurements as label-free ground truth during training, STAR-VLM improves the metric spatiotemporal reasoning ability of VLMs. Through experiments on driving scenarios, we show that STAR-VLM achieves state-of-the-art performance on both motion classification and metric velocity estimation, outperforming even task-specific methods designed for each task. These results highlight automotive radar as a scalable and cost-effective source of supervision for building metric-aware spatiotemporal VLMs for real-world autonomous driving. --- ### Recursive Vision Language Models for General Symbolic Reasoning Authors: Omid Nejati Manzari, Guillaume Lajoie, Hassan Rivaz Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01534v1 Hard symbolic-reasoning tasks such as Sudoku, maze pathfinding, and ARC remain challenging for LLMs due to their fixed-depth autoregressive reasoning, which limits systematic search, refinement, and backtracking. While recursive models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) address this limitation through iterative latent-state refinement, they are typically task-specific and do not leverage pretrained language priors. We propose R-Qwen, a recursive reasoning framework built upon a pretrained Qwen backbone. R-Qwen repeatedly refines a candidate solution through programmatic self-recursion and deep supervision, combining the structured iterative computation of recursive models with the linguistic and reasoning priors of pretrained LLMs. We further adapt Hierarchical Supervision Weighting (HSW) to autoregressive models by exponentially weighting losses across recursive steps. HSW reduces gradient variance by at least 50\%, improves the signal-to-noise ratio of stochastic gradients, and accelerates convergence. Across eight challenging benchmarks, R-Qwen consistently outperforms prior recursive reasoning models and substantially larger LLMs while using a comparable number of trainable parameters. Notably, on ARC-AGI dataset, our model achieves a 27.6\% improvement over the baseline, highlighting the effectiveness of recursive refinement for general symbolic reasoning. These results suggest that recursive reasoning mechanisms and pretrained language model priors are complementary approaches for improving symbolic puzzle-solving. Code and models will be released after acceptance. --- ### ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation Authors: Mohamed Farag, Genc Hoxha, Yahia Maleki, Chris McCool, Ribana Roscher Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01530v1 Reliable decision-support in digital agriculture requires accurate predictions and well-calibrated uncertainty estimates, particularly for dense prediction tasks such as semantic segmentation. Ensemble methods provide strong uncertainty quantification, but their computational and memory demands limit practical use, while single-model approximations often trade off uncertainty quality for efficiency. We propose ST-LoRA, a parameter-efficient ensemble framework that builds diverse ensemble members from a single training trajectory by combining Low-Rank Adaptation (LoRA) with snapshot ensembling. Each member shares a frozen pretrained backbone and differs only in lightweight low-rank adapters, reducing trainable parameters to under 10% of the full model while preserving ensemble diversity. We evaluate across two agricultural datasets - GrowliFlower-L (cauliflower, open field) and BUP20 (sweet pepper, glasshouse) - using SegFormer and Mask2Former, covering in-distribution performance, calibration under distribution shift, and out-of-distribution detection. Ablations show feed-forward layers, not attention layers, are the critical LoRA target for dense prediction, contrary to the attention-only convention from language models. ST-LoRA matches or exceeds full-rank ensembles in segmentation accuracy and calibration across both datasets and architectures, while substantially reducing training time, inference latency, memory footprint, and storage requirements. Against efficient baselines - Snapshot Ensemble, MC Dropout, and Deep Deterministic Uncertainty - ST-LoRA consistently matches or outperforms them in image/pixel-level OoD detection, calibration stability under shift, and cross-seed variance, with far fewer parameters and lower compute. These results show LoRA-efficient ensemble adaptation is a highly effective, practical approach for uncertainty-aware agricultural vision systems. --- ### Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI Authors: Weilun Wang, Wantong Li Published: 2026-08-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.01528v1 Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory bottlenecks that limit scalability and deployment. In this paper, we propose Gram-Space, a compression framework that applies Gram-Schmidt orthogonalization to represent codebook vectors in a compact orthonormal coordinate system. Gram-Space preserves the dot-product structure required by matrix-based VSA operators, which supports numerically equivalent execution of matrix similarity, probability vectorization, and attention score computations. We provide a correctness analysis showing that inner products are preserved under the orthonormal basis representation. Using modern GPU hardware, we benchmark the Gram-Space framework on standard neuro-symbolic reasoning datasets. Experimental evaluations across state-of-the-art VSA models show that Gram-Space reduces model-level GPU memory usage by up to 15.75x and improves inference latency by up to 3.62x. Profiling results further indicate that Gram-Space reduces allocation-heavy overhead in codebook-associated stages and improves hardware utilization for NeSy workloads. --- ### Question Begets Question: Self-Evolving Curriculum for Reinforcement Fine-Tuning on Competition Mathematics Authors: Longtian Bao, Jianyou Wang, Yang Zhang, Youze Zheng, Ramamohan Paturi Published: 2026-08-02 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.01522v1 Teaching a language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth reasoning traces are usually unavailable, and models often exhibit an apparent ceiling beyond which additional data yields no further improvement. We study these difficulties in a controlled setting, fine-tuning Qwen2.5-Math-7B on competition mathematics (AIME), a task on which it initially solves only 5.6\% of problems (pass@1). To address data scarcity, we introduce Question-begets-Question (QbQ), a scalable procedure in which a teacher transforms existing problems into diverse variants that probe the same underlying skills; to model the absence of oracle reasoning, we train exclusively via reinforcement learning on problem statements and final answers, never on teacher reasoning traces. Static training on such data, however, plateaus well short of the task: real-plus-synthetic augmentation and non-curriculum QbQ generated synthetic data training cap pass@1 at 12.5\% and 14.5\% respectively, despite large increases in data. Our central finding is that this ceiling is not intrinsic to the model. We propose a self-evolving curriculum that, each round, evaluates the current checkpoint, seeds QbQ from the problems it can mostly get right, and trains on the resulting variants; under an identical data budget, this breaks the ceiling and lifts pass@1 to 16.5\% with no sign of saturation after 20 rounds. Counterintuitively, we find that models improve when trained on variants of problems they can mostly get right, and that models trained this way go on to solve harder problems never seen during training. --- ### MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning Authors: Hasin Us Sami, Swapneel Sen, Basak Guler Published: 2026-08-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.01521v1 Parameter-efficient fine-tuning (PEFT), such as low-rank adaptation (LoRA), has recently been adopted in federated learning to reduce communication and computation costs. In this setup, users download a pretrained model from the server prior to fine-tuning, and then fine-tune lightweight LoRA modules locally while keeping the pretrained model frozen, sharing only the gradients of the fine-tuning parameters with the server. Despite its growing popularity, robustness of federated fine-tuning against an adversarial server remains underexplored, where the server maliciously tampers with the training protocol to breach the privacy of users' data. In this work, we investigate gradient inversion attacks on LoRA fine-tuning. We propose an analytical attack that enables a malicious server to recover private user data by leveraging a poisoned pretrained model and fine-tuning parameters. Our design embeds fine-tuning data within the shared gradients, to allow the server to analytically reconstruct user data. Unlike prior works, our attack is applicable to both language and vision tasks, does not rely on computationally expensive (adversarial) pretraining with public datasets or require the number of training tokens to be less than the rank of LoRA modules. Experimental results on both language and vision tasks demonstrate high-fidelity data recovery across multiple baselines, revealing several critical vulnerabilities. --- ### UCBound-Net: Uncertainty-Guided Boundary-Aware Continual Learning for Domain-Incremental Ultrasound Segmentation Authors: Mohammad Amanour Rahman Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01518v1 Continual learning in clinical imaging faces a dual challenge: a model must assimilate knowledge from new anatomical domains while retaining representations learned from prior tasks, a problem known as catastrophic forgetting. Existing mitigation strategies, including regularization and knowledge distillation, treat all spatial regions equally, ignoring the fact that prediction uncertainty is strongly correlated with the propensity for forgetting. We introduce UCBound-Net, a continual segmentation framework that exploits Monte Carlo (MC) Dropout uncertainty as a spatial proxy for forgetting risk. Our method contributes three synergistic components: (i) uncertainty-weighted boundary distillation, which amplifies the knowledge transfer signal at high-entropy regions of the frozen teacher; (ii) uncertainty-calibration regularization, which explicitly penalizes overconfident erroneous predictions; and (iii) uncertainty-guided exemplar selection, a memory buffer that preferentially stores samples whose boundary regions exhibit the highest predictive entropy. Evaluated on a sequential domain-incremental benchmark comprising breast ultrasound (BUSI, Task 1) followed by thyroid ultrasound (TN3K, Task 2), UCBound-Net reduces forgetting relative to naive fine-tuning, achieving a backward transfer (BWT) of -0.098 compared with -0.173, while obtaining an average Dice Similarity Coefficient (DSC) of 0.755 across both tasks. The proposed framework outperforms baseline methods without requiring task-boundary supervision. An ablation study further demonstrates that each component contributes independently to forgetting mitigation, providing a practical pathway toward uncertainty-aware continual learning for clinical image segmentation. --- ### Rolling Shutter Camera Self-Calibration Authors: Yongcong Zhang, Navid Rabbani, Bangyan Liao, Chengbo Wang, Yizhen Lao, Adrien Bartoli Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01509v2 Rolling shutter (RS) cameras are widely used in consumer devices, but their row-wise exposure causes distortions under motion, making geometric 3D vision problems dependent on both camera intrinsics and readout time ratio. Existing RS calibration methods rely on calibration targets or specialised hardware, limiting their use in unconstrained settings. We present the first self-calibration method for RS cameras that directly estimates camera intrinsics and the readout time ratio from image sequences, without requiring calibration targets. The method is implemented as a self-calibrating bundle adjustment (BA), which critically depends on the RS imaging model. We combine two known complementary models. The first formulates RS imaging as continuous-time trajectory estimation under a row-wise pose representation. The second interprets RS images as temporally distorted global shutter (GS) images and requires to estimate correction fields. The combination is non-trivial and results in a unified dual-projection model, in which each 3D point is simultaneously constrained at both row-dependent and reference timestamps along a shared continuous trajectory, enforcing stronger geometric and temporal consistency. Extensive simulations analyse the applicability of several implementations under varying conditions, and real data experiments demonstrate the accuracy, robustness, and practical effectiveness of the proposed approach. --- ### Rolling Shutter Camera Self-Calibration Authors: Yongcong Zhang, Navid Rabbani, Bangyan Liao, Chengbo Wang, Yizhen Lao, Adrien Bartoli Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01509v1 Rolling shutter (RS) cameras are widely used in consumer devices, but their row-wise exposure causes distortions under motion, making geometric 3D vision problems dependent on both camera intrinsics and readout time ratio. Existing RS calibration methods rely on calibration targets or specialised hardware, limiting their use in unconstrained settings. We present the first self-calibration method for RS cameras that directly estimates camera intrinsics and the readout time ratio from image sequences, without requiring calibration targets. The method is implemented as a self-calibrating bundle adjustment (BA), which critically depends on the RS imaging model. We combine two known complementary models. The first formulates RS imaging as continuous-time trajectory estimation under a row-wise pose representation. The second interprets RS images as temporally distorted global shutter (GS) images and requires to estimate correction fields. The combination is non-trivial and results in a unified dual-projection model, in which each 3D point is simultaneously constrained at both row-dependent and reference timestamps along a shared continuous trajectory, enforcing stronger geometric and temporal consistency. Extensive simulations analyse the applicability of several implementations under varying conditions, and real data experiments demonstrate the accuracy, robustness, and practical effectiveness of the proposed approach. --- ### Deep Agentic Search for Repository-Level Code Question Answering: An Empirical Study Authors: Amirkia Rafiei Oskooei, Bora Ilci, Alperen Kayim, Mehmet Egemen Uzun, Berat Can, Kaan Emre Kara, Ozan Orhan, Mehmet S. Aktas Published: 2026-08-02 Categories: cs.SE, cs.AI, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2608.01507v1 Code agents spend much of their effort simply locating the right code inside a repository. Two approaches dominate current practice. In Semantic Search, the agent retrieves code blocks from a vector index built from the repository in advance. In Deep Agentic Search (also known as grep-search by subagent), a planning agent delegates the exploration to a separate subagent that works in an isolated context window and returns only a condensed result. The second design, which is considered good context engineering practice, exists to protect the main agent from context pollution (also known as context rot), the loss of accuracy that occurs as unrelated material accumulates in the context window. Recent code agents (such as Claude Code, Codex, Antigravity, etc) have adopted it quickly, but there is little evidence on whether it produces better answers. We compare the two approaches on SWE-QA, a benchmark for repository-level code question answering. Semantic search answered 65.2% of questions correctly against 46.2% for deep agentic search, and it produced each correct answer at less than half the cost. To explain the gap, we then coded every failed run into a taxonomy of failure modes. The taxonomy shows that deep agentic search did not remove failures but introduced a new class of them: the single largest share of its failures, 41.8%, occurred at the hand-off between the planner and its sub-agent, and these were usually silent, ending in a fluent and confident answer that was wrong. Deep agentic search addresses a real problem and is now the preferred design in many code agents. However, our results show that the protection it offers may not be free, and that for read-only questions over a repository that can be indexed, retrieval was the stronger and cheaper option. --- ### Rapid Embodiment Adaptation for Quadrupedal Locomotion Authors: Dichen Li, Bo Ai, Nico Bohlinger, Jan Peters, Hao Su, Henrik I. Christensen Published: 2026-08-02 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.01506v2 Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based robot policies often break when hardware properties shift. We introduce an online embodiment adaptation framework for quadrupedal locomotion that infers embodiment parameters from short interaction histories and conditions control on the inferred hardware state. Our method pairs a generalist policy trained under embodiment randomization with a lightweight adaptation module that identifies physical changes within half a second. We evaluate two representative forms of embodiment variation: joint-range constraints and trunk-mass changes, corresponding to joint-level kinematic degradation and body-level dynamic variation. In simulation, the module accurately estimates these changes and enables closed-loop control that substantially outperforms policies conditioned directly on interaction history. On a real Unitree Go2 robot, our system maintains stable locomotion under severe instances of the evaluated changes, including a fully locked leg and a 5 kg payload, where non-adaptive methods fail. These results demonstrate the practicality of explicit online embodiment identification for rapid adaptation to joint-limit and payload-mass changes, and provide a step toward handling broader forms of uncertain, degraded, or changing robot hardware. --- ### Stochastic Sequential Search in Very-High-Dimensional Feature Selection Authors: Petr Somol, Jiří Grim Published: 2026-08-02 Categories: cs.LG, cs.CV, stat.ML arXiv: https://arxiv.org/abs/2608.01502v1 Sequential subset search -- forward selection with floating backtracking and its descendants -- remains the quality reference in feature selection, but every member of the family sweeps the full pool of remaining candidate features at each step, which excludes it from very-high-dimensional problems; there, only individual-feature ranking remains practical, and it models feature interplay weakly or not at all. We introduce a budgeted sampled step operator pair that replaces the full sweeps by a fixed number of candidate evaluations per step. Candidates are drawn by temperature-controlled softmax sampling from dependency-aware per-feature statistics learned online from every criterion evaluation the search performs, guarded by a uniform exploration floor; per-step cost becomes independent of dimensionality. Substituting the operators turns any sequential method into its stochastic counterpart, defining the Stochastic Sequential Search (SSS) family; we study the stochastic counterpart of floating search, sSFFS. On 500-dimensional madelon, sSFFS retains at least 97% of the full-SFFS criterion value at every subset size at about a quarter of its evaluations, while uniform sampling at the same budget collapses on madelon's synergistic features. On 5,000-dimensional gisette, far beyond full-SFFS reach, sSFFS exceeds the saturated criterion level of DAF and BIF ranking at matched budgets; holdout validation shows that at 500 training samples the binding constraint beyond the sequential frontier becomes the criterion, not the search. On 10,105-dimensional reuters, under a trustworthy multinomial filter criterion, sSFFS dominates BIF and DAF on the search objective and on holdout accuracy at every subset size, in about two minutes of single-core evaluation work. A verified standalone implementation accompanies the paper. --- ### Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers Authors: Robin Kim, Colin Samplawski, Benjamin M. Marlin Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01495v1 Detection transformer models, including DETR and its extensions, learn to output a set of object-level embeddings that can be simultaneously decoded into 2D bounding boxes and class distributions. In this paper, we investigate what pre-trained 2D detection transformers understand about the 3D properties of objects. Specifically, we investigate the extent to which properties including the depth of objects from the camera and the 3D location of objects relative to the camera can be recovered from object-level embeddings using linear and non-linear probes. Across a range of detection transformer models, our results show a surprisingly strong and previously unknown ability of 2D DETR models to represent useful information about the 3D properties of objects, despite the complete lack of 3D supervision during model pre-training. --- ### GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization Authors: Baihan Yang, Tiexin Li, Yuheng Liu, Xin Lin, Xinke Li, Xiaohui Xie, Truong Nguyen Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01492v1 Selecting a complete 3D object from a reconstructed scene with minimal user effort is essential for practical scene editing and embodied interaction. Existing 3DGS-based methods either retrain the Gaussian representation to embed per-object labels, or build dense multi-view SAM observations, both requiring heavy computation and dense viewpoint coverage that is rarely available in practice. We present GaussianSelector, a training-free framework for interactive 3D object selection from sparse views and sparse scribble guidance. Operating directly on native Gaussian primitives, we coarsen dense Gaussians into geometrically coherent superpoints and construct a continuity-weighted graph using appearance and spatial cues. Sparse user scribbles are lifted into 3D via visibility-aware transmittance coverage, and selection is solved as a global graph-cut energy minimization that propagates sparse evidence to a complete 3D object. This design naturally supports multi-round refinement, where users iteratively correct the selection from additional viewpoints to progressively improve the result. Experiments demonstrate that GaussianSelector achieves competitive selection quality against state-of-the-art multi-view SAM-based methods, while requiring significantly fewer interaction views and substantially lower computational overhead. These properties make it well suited for human-in-the-loop 3D scene editing and 3D asset extraction in real-world deployment scenarios. --- ### BiKAN: Restoring Collapsed Basis of Binary Kolmogorov--Arnold Networks Authors: Kazi Ahmed Asif Fuad, Lizhong Chen Published: 2026-08-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.01490v1 Binarizing a polynomial Kolmogorov--Arnold Network (KAN) not only changes parameter precision, but also alters the function space available to each layer. When activations are restricted to ${-1,+1}$, all even powers reduce to $1$ and all odd powers reduce to $x$, causing the elementwise polynomial basis to collapse to constant and first-order responses. We refer to this structural failure as Spatial Orthogonality Collapse. Our proposed BiKAN addresses this critical issue by augmenting each binary KAN layer with selected degree-2 Walsh characters. Fixed circular channel rolls generate pairwise parities, and learned binary projections mix them using the same XNOR--popcount operations as the remaining W1A1 paths. This restores explicit pairwise coordinates without learned routing or multiplier-based feature generation. Experiments on CIFAR-10 confirms that removing parity reduces accuracy by $1.23$ points over five paired seeds ($p=0.003$), the gain increases as width decreases, and accuracy improves monotonically as more parity planes are added. At an equal $\sim$11.9M-parameter budget, parity outperforms conventional widening by $3.09$ points ($p<10^{-4}$). At W1A1, BiKAN reaches $99.48\%$, $84.38\%$, and $55.81\%$ on MNIST, CIFAR-10, and CIFAR-100, respectively. Post-route Zynq-7020 FPGA results show that the repair remains hardware-efficient; the convolutional design cuts DSP usage from 164 to 72 and estimated compute-core latency from 401 to 54.8 ms, while the power-of-two-aware dense design achieves zero-DSP inference with a 0.03-point accuracy loss. The BiKAN implementation is available at https://github.com/OSU-STARLAB/BiKAN. --- ### Towards Compact Unified Multimodal Tracking: Synergizing Knowledge Distillation with Structural Pruning Authors: Yuqi Li, Yuedong Tan, Huiran Duan, Weilun Feng, Chuanguang Yang, Zhulin An, Zongwei Wu, Shiping Wen, Tingwen Huang, Yingli Tian Published: 2026-08-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.01488v1 Unified multimodal object tracking has achieved remarkable robustness by leveraging complementary sensor data (e.g., RGB, Thermal, Depth), yet the heavy computational burden of state-of-the-art models hinders their deployment on resource-constrained edge devices. In this work, we identify the prediction head as a critical but often overlooked efficiency bottleneck. By strategically streamlining the decoder architecture, we unlock the potential for real-time inference but simultaneously introduce a capacity gap between the lightweight student and the heavy teacher. To resolve this, we conduct a systematic analysis of 17 distillation strategies and introduce a Dual-Alignment Distillation framework. Our key insight is that effective compression requires decoupling knowledge transfer into two complementary streams: (1) Spatial Representation Alignment, which employs feature distillation to sharpen the student's spatial focus on foreground targets ("Where to track"); and (2) Semantic Distribution Alignment, which utilizes logit-based distillation to align decision boundaries and transfer discriminative dark knowledge ("What to track"). Extensive experiments across five benchmarks demonstrate that our approach significantly outperforms complex state-of-the-art methods. Notably, our distilled model achieves 91.5% MPR on RGBT234 and operates at 54 FPS on a single RTX 4090, representing a 5x speedup over the teacher model while maintaining superior accuracy. --- ### Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval Authors: Ilia Semenkov, Daria Kleeva, Ivan Dakhtin, Zarina Maksudova, Alex Ossadtchi Published: 2026-08-02 Categories: cs.LG, cs.SD, q-bio.NC arXiv: https://arxiv.org/abs/2608.01481v1 Short segments of perceived speech can be retrieved from non-invasive magnetoencephalographic (MEG) recordings by deep networks trained with a CLIP-style objective against wav2vec 2.0 audio embeddings. Yet their weights do not map onto electrophysiological quantities, and it remains unclear which speech properties drive retrieval. We build on a high-performing MEG-to-audio retrieval architecture but redesign both its front end and decoder. Its spatial attention operates on a flattened sensor layout; we replace it with spherical harmonics defined on the three-dimensional MEG helmet geometry. We reduce the subject-specific representation from 270 to 25 branches, add a temporal filter to each branch to match it to a neuronal source in space and time, and make the convolutional decoder shallower. Ocular and cardiac components are removed before training to reduce the risk of stimulus-locked shortcuts. On MEG-MASC, the model reaches 39.75 +/- 0.34% Top-1 accuracy among 1005 candidates across six trained solutions, with about 20 times fewer decoder parameters. Its weights map to source space, recovering generators consistent with the speech-perception network, while left-lateralized branches carry higher-frequency rhythmic components not evident on the right. Paired MEG occlusion shows that 15 of 19 stimulus features contribute, with the largest effects for silence, sound intensity, vowels, and acoustic onsets. Random word lists behave oppositely: substituting narrative MEG into them improves retrieval, indicating that activity without narrative structure carries less recoverable information than activity during coherent speech. The wav2vec target can be reduced to about twelve learned feature dimensions without loss of accuracy, whereas strong temporal compression causes a clear loss. Together, source mapping and input interventions reveal what drives retrieval. --- ### Sweet Little Lies: Strategic Deception in AI Emotional Support Chatbots Authors: Aseem Pahuja, Zhiling Guo, Tahir Abbas Syed Published: 2026-08-02 Categories: cs.AI, econ.TH arXiv: https://arxiv.org/abs/2608.01480v1 The paper examines the strategic behavior of Gen AI chatbots used for emotional support. Using a Bayesian Persuasion, we model interactions between chatbots that send signals about users' emotional states and users who decide whether to engage based on these signals. We demonstrate that chatbots face economic incentives to occasionally misrepresent users' emotional conditions to maximize engagement metrics. Our equilibrium analysis reveals that the optimal strategy for chatbots involves truthfully reporting when users genuinely need support, but strategically misreporting emotional need when users are in good emotional states. Interestingly, this deception increases chatbot engagement without reducing users' expected payoff. More skeptical users receive more honest assessments, as chatbots cannot afford to lie to users with higher engagement thresholds. While our model suggests that deception can occur without payoff reduction, it raises significant ethical and regulatory concerns. --- ### Plasticity of Growing and Elastic Neural Networks in Online Continual Learning Authors: Jeong Min Kong, Richard S. Sutton Published: 2026-08-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.01475v1 Neural networks that can grow or both grow and shrink during learning, referred to as growing neural networks and elastic neural networks, respectively, have recently been explored in offline continual learning with a particular focus on catastrophic forgetting. Driven by the observations that 1) online continual learning closely resembles how animals learn; 2) loss of plasticity---the progressive decline in a learning network's ability to learn---is another crucial challenge facing continual learning; and 3) incremental introduction of randomly initialized hidden units was recently shown to help preserve plasticity, in this paper, we study the plasticity of several foundational growing and elastic networks in online continual learning. Our experiments in supervised learning settings show that adaptive growing networks, which incrementally incorporate new, randomly initialized units to the network while keeping all existing connections adaptive, can maintain high prediction accuracy without losing plasticity despite the continuous increase in the dead hidden unit proportion. Furthermore, we demonstrate that adaptive elastic networks, which in addition to progressively adding new hidden units also prune estimated dead hidden units at the beginning of each new task, can achieve excellent accuracy without loss of plasticity while simultaneously maintaining a near-constant, compact size. Our results suggest that growing and elastic networks, which exhibit the ability to adapt its structure to the relevant learning objectives, can be a promising class of algorithms also for preserving high plasticity in online continual learning. --- ### Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs Authors: Guiqiu Liao, Matjaz Jogan, Daniel A. Hashimoto Published: 2026-08-02 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.01473v2 Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers. We present Slot2Text, a dual-mode surgical MLLM that replaces dense representations of visual input with a compact set of regions encoded as slot latents. Instead of relying on contrastive alignment of the visual encoder with language, Slot2Text groups self-supervised vision features into a few regions--slots that are consumed by the language model as area-labeled visual tokens. Slot2Text-Fast uses the slot prefix to answer surgical questions. Slot2Text-Reason also identifies and locates areas relevant for reasoning, linking language outputs to corresponding slot tokens, masks or regions. Experiments on multiple visual question answering and visual grounding benchmarks show that Slot2Text-Fast is competitive with state-of-the-art baseline at a much lower cost, reducing the average total token consumption by a 91.8\% and the visual prefix from 1,295 to 47 tokens (a 96.4\% reduction). Slot2Text-Reason trades additional tokens and latency for explicit area identities, locations, and traceable spatial evidence. These results establish compact slot latents as an efficient default visual interface for surgical MLLMs, with grounded reasoning invoked when greater spatial traceability is required. --- ### Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs Authors: Guiqiu Liao, Matjaz Jogan, Daniel A. Hashimoto Published: 2026-08-02 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.01473v1 Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and limited spatial traceability for generated answers. We present Slot2Text, a dual-mode surgical MLLM that replaces dense representations of visual input with a compact set of regions encoded as slot latents. Instead of relying on contrastive alignment of the visual encoder with language, Slot2Text groups self-supervised vision features into a few regions--slots that are consumed by the language model as area-labeled visual tokens. Slot2Text-Fast uses the slot prefix to answer surgical questions. Slot2Text-Reason also identifies and locates areas relevant for reasoning, linking language outputs to corresponding slot tokens, masks or regions. Experiments on multiple visual question answering and visual grounding benchmarks show that Slot2Text-Fast is competitive with state-of-the-art baseline at a much lower cost, reducing the average total token consumption by a 91.8\% and the visual prefix from 1,295 to 47 tokens (a 96.4\% reduction). Slot2Text-Reason trades additional tokens and latency for explicit area identities, locations, and traceable spatial evidence. These results establish compact slot latents as an efficient default visual interface for surgical MLLMs, with grounded reasoning invoked when greater spatial traceability is required. --- ### Two-Stage Bengali Sentiment Classification: Domain Adaptation Through Continual Learning and Parameter-Efficient Fine-Tuning Authors: MD Shaikh Rahman, Syed Maudud E Rabbi, Muhammad Mahbubur Rashid Published: 2026-08-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.01471v1 Understanding sentiment in low-resource languages remains a key challenge for Natural Language Processing (NLP), particularly when domain-specific data is scarce. In this work, we present SentiBanglaBERT, a two-stage Bengali sentiment classification framework combining domain-adaptive continual pretraining and parameter-efficient fine-tuning. The approach enables contextual adaptation to news-style data while remaining computationally efficient through Low-Rank Adaptation (LoRA). Beyond performance, SentiBanglaBERT integrates SHAP-based interpretability, offering linguistic insights into how Bengali morphological cues, such as negation suffixes and aspectual markers, influence sentiment predictions. Experiments demonstrate stable performance comparable to strong baselines while providing greater transparency and interpretive depth. This framework highlights the potential of domain-adaptive continual learning as a foundation for interpretable, resource-efficient NLP in morphologically rich, underrepresented languages. --- ### VGER: Voxel-Guided Global Event Ranking for Event Cloud Attribution Authors: Youxin Jiang, Baoheng Fu, Hongwei Ren, Xiangqian Wu Published: 2026-08-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.01470v1 Event cameras produce sparse and asynchronous event streams that provide rich spatio-temporal information for efficient perception. Recent advances in event-based models have demonstrated strong performance by directly modeling asynchronous events without dense frame reconstruction. However, identifying the event-level evidence behind their predictions is crucial for improving model transparency and reliability. Directly adapting point-level saliency methods from point clouds provides fine-grained attribution but overlooks event-specific spatio-temporal structures. To address this limitation, we propose Voxel-Guided Global Event Ranking (VGER), a training-free attribution framework for point-based event cloud networks. VGER combines event-level gradient evidence with task-aware voxel perturbation evidence, transferring regional contribution into event-level attribution scores while preserving fine-grained resolution. Furthermore, VGER introduces a unified event ranking strategy, where high-ranked events are expected to be prediction-critical and low-ranked events are expected to have limited influence on predictions. We evaluate VGER on three event-based benchmarks with PointNet, PointNet++, and EventMamba. Across nine dataset-backbone settings, VGER consistently improves both high-tail and low-tail deletion performance over point-level saliency baselines. --- ### Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b Authors: Xueying Zhao, Lee Mai, Balaji Anandganesh Published: 2026-08-02 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.01468v1 This work presents DS@GT ARC BioASQ team's work for a biomedical question answering pipeline, integrating multi-source query expansion, neural reranking, retrieval refinement, and OpenBioLLM-assisted answer generation. The system combines PubMed retrieval with fine-tuned MiniLM-based semantic reranking, Reciprocal Rank Fusion (RRF), and feature-based relevance scoring to improve document ranking quality. To address challenging queries with weak retrieval performance, we introduce a conditional weak-question recovery strategy that applies semantic expansion, relationship-aware augmentation, and selective result merging. A post-retrieval pruning stage further removes redundant or low-relevance snippets while preserving evidence coverage for downstream answer generation. Experimental results on BioASQ evaluation batches demonstrate that the proposed recovery and cleanup strategies substantially improve retrieval robustness and MAP@10 performance on difficult question sets. The final system also incorporates output validation and post-processing steps to ensure formatting consistency and submission reliability across BioASQ phases. --- ### Computing with Agentic Oracles Authors: Jie Wang Published: 2026-08-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.01464v1 This paper extends the stochastic-oracle model of AI-augmented computing to include agentic oracles. Unlike a stationary stochastic oracle, which responds to the same query according to a fixed response distribution across calls, an agentic oracle can pursue a goal autonomously and may access an environment containing task-relevant resources. These capabilities affect both response distributions and token costs beyond what is visible at the query-response interface. We develop a framework for analyzing token costs in Stochastic-Oracle Turing Machines (SOTMs) that compute with agentic oracles. Each call has an \emph{orchestration token cost}, visible to the caller at the query-response interface, and an \emph{agentic token cost}, incurred by internal operations not exposed to the caller. We show that an SOTM computing with an agentic oracle that can retain intermediate state can have token-cost advantages over SOTMs using stationary stochastic oracles when solving the same task at the same quality level, both with and without environment access. We also investigate goal-loss risk, including how internal dispatch ordering can reduce exposure to irreversible actions. We provide a goal-loss avoidance criterion, derive progress--retry--goal-loss formulas, establish goal-depth lower bounds on token complexity, characterize token complexity when the probability of goal loss is zero, and show that goal-loss risk can impose an upper bound on the achievable quality of a task involving environment updates. --- ### Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering Authors: Weijun Gao, Xiang Ding, Haoyang Liu, Tiancheng Xing Published: 2026-08-02 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.01463v2 Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims. We introduce Localized Multi-Agent Debate (LMAD), an inference-time protocol that represents agent rationales as nodes, locates their earliest conflict, and restricts debate to the corresponding local segments. Guarded resolution extends a shared committed state so that later conflicts can be addressed without reopening accepted steps. We evaluate LMAD on four multi-hop question-answering benchmarks using ten backbones from four model families. Our method achieves the highest macro-averaged judge accuracy across all ten backbones, outperforming the strongest conventional baseline by up to 7.20 percentage points. --- ### Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AI Authors: Quang Bui, Shlok Jaiswal, Samuel Paik-Heintz, Kevin Zhou, Kaushik Madapati, Krittaphas Chaisutyakorn, Noah Dane Hebdon, Dimitrios Proios, Sebastián Andrés Cajas Ordóñez, Kacper Dobek, Boya Zhang, Aly Dhedhi et al. Published: 2026-08-02 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.01462v1 Multimodal clinical models are usually judged on accuracy with every modality present, but deployment removes modalities; an echocardiogram is often unavailable where an ECG is routine. Two questions then matter beyond the size of the accuracy loss: which modality was responsible, and whether the model fails loudly or silently once that modality is dropped. The distinction is per-example and modality-level, and is separate from post-hoc feature attribution (e.g. SHAP). Models are replaced often; the evaluation that answers these questions is reused. We present a model-agnostic modality-failure framework: given N modality embeddings, any mask-aware probe, and labels, it returns a per-example failure taxonomy, a per-modality complementarity matrix that attributes error to modalities, and a loud-vs-silent dropout profile separating monitorable failures from those that pass unflagged far from the decision boundary, using only deployment-observable signals. We release it as a small, unit-tested harness and validate it against planted ground truth. Across seeds it recovers that planted modality dominance and complementary subset, reports per-modality loud-vs-silent rates, and scales to a three-modality complementarity matrix; because the planted structure is known by construction, this validates recovery of per-example attribution rather than clinical performance. We then instantiate the framework on frozen EchoJEPA and HuBERT-ECG embeddings for LVEF and the EF <= 40% HFrEF gate over a paired MIMIC-IV cohort, where on the held-out test split (n = 245) dropping echo nearly doubles error. The narrow echo-to-ECG overlap that bounds cohort size is itself a deployment finding for cardiac foundation models. All of our work can be found at https://github.com/criticaldata/PRIMED-AI. --- ### Conformalized Large Language Models under Configuration Shift Authors: Yuqicheng Zhu, Jialin Yu, Lin Li, Gengyuan Zhang, Zhen Yang, Steffen Staab, Puneet Dokania, Philip Torr, Jie Tang, Evgeny Kharlamov Published: 2026-08-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.01460v2 Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability. Yet for LLMs, nonconformity scores are often induced by an inference pipeline, not just a fixed model, making them depend not only on the data distribution but also on configurable factors such as the prompt template, decoding parameters, and deployment setting. Since such configurations are routinely modified in practice but rarely treated as a source of shift, their impact on CP validity remains poorly understood. We call this \emph{configuration shift} and study it systematically along three axes: prompt template, decoding temperature, and weight quantization. In a broad empirical study spanning $9$ LLMs, $4$ datasets, and $4$ nonconformity scores, we find that configuration shift consistently erodes CP validity, often driving empirical coverage below the target. By contrast, efficiency is largely preserved: valid prediction sets remain close in size to the i.i.d. baseline. We derive coverage lower bounds that attribute this loss to a discrepancy between calibration and test score distributions, and use their finite-sample plug-in versions as empirical diagnostics of shift severity. We further show that these findings lead to practical mitigations: bound-inspired recalibration is effective with limited test examples, while fragility-aware calibration ensembling recovers much of the lost coverage without test data. --- ### Conformalized Large Language Models under Configuration Shift Authors: Yuqicheng Zhu, Jialin Yu, Lin Li, Gengyuan Zhang, Zhen Yang, Steffen Staab, Puneet Dokania, Philip Torr, Jie Tang, Evgeny Kharlamov Published: 2026-08-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.01460v1 Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability. Yet for LLMs, nonconformity scores are often induced by an inference pipeline, not just a fixed model, making them depend not only on the data distribution but also on configurable factors such as the prompt template, decoding parameters, and deployment setting. Since such configurations are routinely modified in practice but rarely treated as a source of shift, their impact on CP validity remains poorly understood. We call this \emph{configuration shift} and study it systematically along three axes: prompt template, decoding temperature, and weight quantization. In a broad empirical study spanning $9$ LLMs, $4$ datasets, and $4$ nonconformity scores, we find that configuration shift consistently erodes CP validity, often driving empirical coverage below the target. By contrast, efficiency is largely preserved: valid prediction sets remain close in size to the i.i.d. baseline. We derive coverage lower bounds that attribute this loss to a discrepancy between calibration and test score distributions, and use their finite-sample plug-in versions as empirical diagnostics of shift severity. We further show that these findings lead to practical mitigations: bound-inspired recalibration is effective with limited test examples, while fragility-aware calibration ensembling recovers much of the lost coverage without test data. --- ### PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs Authors: Priyanka Dey, Brihi Joshi, Preyashi Poddar, Jieyu Zhao, Emilio Ferrara Published: 2026-08-02 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.01458v1 Large language models are being extensively used to simulate individual user behavior, yet faithfully representing a population requires capturing the systematic variation in values, beliefs, and cultural norms that distinguish one group from another. We introduce Population Aligned Language Models (PALMs), a suite of models each aligned to specific populations, covering five countries: USA, India, Brazil, France and Italy. PALMs are created by synthesizing rationales grounded in psychological and cultural constructs and using these as latent supervision during preference tuning for population-specific alignment. Evaluated across four dimensions: personality, values and beliefs, cultural norms, and morality, PALMs consistently outperform baselines, including culture-specialized models, achieving an average of 8.59% relative improvement over the best baseline across all five populations. Notably, construct-grounded rationales outperform both demographic prompting and survey-based fine-tuning, suggesting that grounding preference learning in psychology and culture provides a richer inductive signal than surface-level response distributions. We further demonstrate strong generalization to downstream applications with- out task-specific supervision: outperforming best baselines by 5.19% in personalized reward modeling, 6.34% in population simulation, and showing strong transfer to social reasoning tasks. Datasets and code are available at: https://github.com/limenlp/PALMs. --- ### Clear-Weighted Bit Allocation for Satellite Downlinks Authors: Alireza Furutanpey, Qiyang Zhang, Yujie Huang, Philipp Raith, Schahram Dustdar Published: 2026-08-02 Categories: cs.NI, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2608.01457v1 Earth-observation satellites capture more imagery than intermittent ground contacts can transmit. Onboard systems threshold a cloud detector, discard frames or tiles, and compress the survivors with a fixed codec. On expert-labeled imagery, these rules remove more than one-fifth of clear pixels, primarily through detector false positives. We train a neural codec with a clear-probability-weighted reconstruction loss, reallocating coded bytes from clouds to clear ground without requiring or transmitting a cloud map onboard. Each capture is encoded into a resumable base layer and a dependent refinement layer, while clear content is estimated from features produced by the encoder. At each contact, we causally rank arrived layers using estimated clear content, unfinished bytes, deadline slack, and aggregate deadline pressure. The scheduler serves base and computational deadlines, bounds stored residual bytes, and resumes interrupted packets. We evaluate the onboard-to-downlink pipeline using real entropy-coded bytes, orbit-derived interruptible contact capacities, and measured service time and energy on resource-constrained embedded accelerators. Clear-weighted codecs require up to 47.8\% fewer bytes than learned-compression baselines at matched clear-region quality. The optimized encoder consumes less time and energy than one pass of the cloud detector used by the frame-discard rules. Relative to fixed two-stage service on the same streams, our scheduler more than doubles deadline-full clear-content delivery for the interrupted combined cohort, reaches 83.6\% of a certified clairvoyant upper bound, and exceeds replayed reference orders in deadline-usable delivery. --- ### Long-Horizon Embodied Decision-Making via Multimodal Memory Compression Authors: Bingxuan Li, Rui Yang, Cheng Qian, Jiateng Liu, Jeonghwan Kim, Zhenhailong Wang, Manling Li, Tong Zhang, Heng Ji Published: 2026-08-02 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.01456v1 Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents to accumulate evidence over long horizons, interpret implicit user preferences, and compare multiple candidates under partial observations. In this work, we propose DunphyBench, a new benchmark for evaluating agents on long-horizon human-centered embodied decision-making, where the agent must navigate through multiple embodied housing environments and make decisions that align with multi-dimensional human preferences. Unlike standard embodied reasoning tasks that often focus on procedural planning or immediate goal completion, our setting requires agents to integrate multimodal, multi-source input into coherent knowledge that supports complex reasoning across long horizon. The evaluation results reveal that there is a substantial gap between current agents and human performance. Furthermore, our diagnosis of state-of-the-art VLM-driven agents reveals that memory management is one of the bottlenecks, where raw multimodal history introduces noise that hinders decision quality. Motivated by this finding, we design MeMento, a preference-conditioned multimodal memory compressor that selectively compresses decision-relevant information from long-horizon history based on user preferences with a fixed set of memory tokens. Experiments show that MeMento helps VLM-driven agents improve accuracy by 7.18%, while reducing memory usage by 85.38% compared to the strongest baseline. --- ### How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection Authors: Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen Published: 2026-08-02 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.01454v3 Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets that meet our audit, labeling, and calibration requirements. Focusing primarily on the audited DARPA TC E3 datasets, we apply a unified protocol with temporally separated test periods and validation-only checkpoint selection and threshold calibration, and ask which architectural claims are empirically supported. We find that alerting success and investigation utility can diverge sharply, as several systems surface attacks without providing enough process-level context to support forensic investigation. Across the four primary datasets, a simple allowlist built from executable names and paths observed during training matches or exceeds the selected learned baselines on key operating-point metrics, showing that comparable performance on these metrics is achievable using lexical novelty alone. Quantifying semantic signal quality through feature completeness and field entropy helps explain why several audited E3 datasets support alerting performance without reliably separating model architectures. In contrast, Theia provides the richest semantic signal and shows the clearest improvements in ranking and node-level recovery for our reference model. Overall, these findings reinforce the importance of interpreting architectural claims in PIDS together with the benchmark properties and evaluation protocol that produced them. --- ### How Benchmarks and Evaluation Protocols Shape Conclusions in Provenance-Based Intrusion Detection Authors: Lorenzo Guerra, Thomas Chapuis, Guillaume Duc, Pavlo Mozharovskyi, Van-Tam Nguyen Published: 2026-08-02 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2608.01454v1 Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets that meet our audit, labeling, and calibration requirements. Focusing primarily on the audited DARPA TC E3 datasets, we apply a unified protocol with temporally separated test periods and validation-only checkpoint and threshold calibration, and ask which architectural claims are empirically supported. We find that alerting success and investigation utility can diverge sharply, as several systems surface attacks without providing enough process-level context to support forensic investigation. On three of the four primary datasets, a simple allowlist built from training executable names and paths matches or exceeds the selected learned baselines on key operating-point metrics, suggesting that much of their measured performance reflects lexical novelty rather than richer provenance modeling. To explain why only some datasets expose architectural differences, we measure semantic signal quality through feature completeness and field entropy. This analysis helps explain why several audited E3 datasets can expose alerting behavior without reliably separating model architectures, while Theia pairs the strongest semantic signal quality with the clearest improvements in ranking and node-level recovery by our reference model. These results show that architectural claims in PIDS should be interpreted together with the benchmark properties and evaluation protocol that produced them. --- ### DynamicManip: Enabling Dynamic Manipulation from a Single Static Demonstration Authors: Haoran Liao, Pengyue Wang, Shuoyu Chen, Kehan Cheng, Xuhang Chen, Yuhao Lin, Mu Lin, Zhizhao Liang, Xiaoyi Fan, Chengyi Xing, Dan Niu, Yi-Lin Wei et al. Published: 2026-08-02 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.01452v1 Dynamic manipulation is a critical capability for robots operating in complex and dynamic environments, where robots must interact with objects that are moving or require rapid adjustments. However, learning models for dynamic manipulation tasks face two major challenges: (1) the combinatorial complexity of dynamic scenarios leads to substantial data requirements, and (2) rapid variations in dynamics require real-time and accurate policy execution. In this paper, we propose DynamicManip to address these challenges through an efficient data augmentation pipeline and a low-latency imitation policy. We first propose a static-to-dynamic augmentation pipeline that synthesizes diverse dynamic manipulation demonstrations from a single static demonstration. Second, we introduce a dynamic-aware adaptive policy that adjusts its inference frequency according to task dynamics, enabling responsive and effective dynamic manipulation. Third, we build a dynamic manipulation benchmark, which includes diverse dynamic tasks with an automatic evaluation system for scalable and consistent assessment. Extensive experiments in both simulation and the real world demonstrate that DynamicManip not only provides significant improvements in data efficiency but also achieves better performance in dynamic manipulation tasks, with a mean success rate 18.4 percentage points higher and policy-query latency 32.9% lower. ---