# Research Papers — 2026-08 · bundle page 215 of 240 > Full-text markdown of papers #10701–10750 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/215 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/214.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/216.md) ### Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA Authors: Jiwon Lee, Yong-chan Park, Jungin Hong, U Kang Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03177v1 How can question answering (QA) systems determine whether a query is ambiguous? Ambiguity detection is essential in open-domain QA, as misclassification leads to answering the wrong interpretation or unnecessary clarification. However, existing methods conflate answer diversity with ambiguity, leading to inaccurate predictions. They also process queries uniformly, resulting in wasteful computation. We propose ARCHIVE (Ambiguity Recognition via Cascaded Hypothesis Inspection and Conflict Verification), an accurate and efficient framework that detects ambiguity via logical conflict: a query is ambiguous when its valid answers cannot all be true under a single interpretation. ARCHIVE combines a lightweight early-exit encoder for surface-detectable cases with a conflict reasoning module that models logical relations among answers, reinforced by an invariance objective for robustness to noisy answer sets. We present QuireQA, a 4,703-query benchmark spanning factoid, non-factoid, and ill-formed queries. Experiments show ARCHIVE outperforms competitors, improving F1-amb by up to 10.4% and F1-unamb by up to 21.6%, while operating 16$\times$ faster than the best competitor. --- ### Frequency-Decorrelated Temporal Ensembles for EEG--fNIRS Imagined-Handwriting Decoding Authors: Xiao Fan, Hongbin Guo, Yubo Han, Yi Zhang Published: 2026-08-04 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2608.03176v2 Imagined handwriting offers a temporally rich paradigm for non-invasive neural decoding, yet reliable recognition across unseen participants remains difficult because scalp EEG is noisy and internally generated stroke sequences vary across individuals. The Multimodal Brain-Computer Interface Grand Challenge provides synchronized EEG and fNIRS for four-class subject-independent handwriting-trajectory classification. We propose FRED, a task-adapted system that models imagined handwriting as a multi-second motor sequence and trains a compact multi-scale temporal network on three complementary EEG frequency views. With three seeds per view, cross-band members produce substantially less-correlated errors than same-band replicas, yielding a clean nine-member ensemble accuracy of 0.8076/0.7242/0.7492 on the public/private/overall test partitions without test-set adaptation or output constraints. The submitted pipeline further incorporates transductive pseudo-label training, three EEG-Conformer members, posterior aggregation, and a paradigm-aware decoder. Because every 12-trial randomization block contains three instances of each class, the final predictions are obtained by Hungarian assignment under the known block quota. On one fixed posterior pool, independent, session-constrained, and block-constrained decoding achieve 0.7600, 0.7758, and 0.7952 overall accuracy, respectively. The complete system reaches 0.8498/0.7718/0.7952, ranking fourth on the private split. A modality audit finds fNIRS-only decoding at chance (0.2511 overall), while adding fNIRS to EEG changes accuracy by only +0.0025. These results identify frequency-diverse temporal EEG modeling and protocol-matched structured inference as the principal sources of performance in this sparse-montage EEG--fNIRS setting. The source code is available at https://github.com/XiuFan719/EEG-fNIRS-fuse-method-for-MM-challenge. --- ### Frequency-Decorrelated Temporal Ensembles for EEG--fNIRS Imagined-Handwriting Decoding Authors: Xiao Fan, Hongbin Guo, Yubo Han, Yi Zhang Published: 2026-08-04 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2608.03176v1 Imagined handwriting offers a temporally rich paradigm for non-invasive neural decoding, yet reliable recognition across unseen participants remains difficult because scalp EEG is noisy and internally generated stroke sequences vary across individuals. The Multimodal Brain-Computer Interface Grand Challenge provides synchronized EEG and fNIRS for four-class subject-independent handwriting-trajectory classification. We propose FRED, a task-adapted system that models imagined handwriting as a multi-second motor sequence and trains a compact multi-scale temporal network on three complementary EEG frequency views. With three seeds per view, cross-band members produce substantially less-correlated errors than same-band replicas, yielding a clean nine-member ensemble accuracy of 0.8076/0.7242/0.7492 on the public/private/overall test partitions without test-set adaptation or output constraints. The submitted pipeline further incorporates transductive pseudo-label training, three EEG-Conformer members, posterior aggregation, and a paradigm-aware decoder. Because every 12-trial randomization block contains three instances of each class, the final predictions are obtained by Hungarian assignment under the known block quota. On one fixed posterior pool, independent, session-constrained, and block-constrained decoding achieve 0.7600, 0.7758, and 0.7952 overall accuracy, respectively. The complete system reaches 0.8498/0.7718/0.7952, ranking fourth on the private split. A modality audit finds fNIRS-only decoding at chance (0.2511 overall), while adding fNIRS to EEG changes accuracy by only +0.0025. These results identify frequency-diverse temporal EEG modeling and protocol-matched structured inference as the principal sources of performance in this sparse-montage EEG--fNIRS setting. The source code is available at https://github.com/XiuFan719/EEG-fNIRS-fuse-method-for-MM-challenge. --- ### Attribute-based Undetectable Watermarking for Generative AI Models Authors: Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel, Er-Cheng Tang Published: 2026-08-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.03174v1 Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs. Existing cryptographic watermarking methods provide strong undetectability guarantees: without a detection key, watermarked outputs are computationally indistinguishable from unwatermarked ones. However, these approaches do not address the crucial deployment challenge of how to safely delegate detection capabilities. With an unrestricted detection key, a malicious detector may use the detection key beyond its intended scope, enabling watermark sanitization, scope abuse, and user profiling. To mitigate this safety concern, we introduce, to the best of our knowledge, the first \emph{attribute-based watermarking} for generative AI models, providing fine-grained, policy-controlled watermark detection. In our approach, each generated output is associated with attributes, and each detection key is \emph{constrained by a policy} on potential attributes. A detection key can only be used to detect watermarked outputs whose attributes satisfy the corresponding policy, while watermarked outputs that fall outside the policy remain computationally indistinguishable from unwatermarked ones. We construct such an attribute-based watermarking scheme and formalize its security properties, including consistency, adaptive robustness to bounded corruptions, undetectability, and soundness, along with a security proof under standard cryptographic assumptions. Our construction integrates constrained pseudorandom functions, pseudorandom error-correcting codes, and randomness recovery procedures with generative AI models. Finally, we implement a prototype and an empirical evaluation, demonstrating that attribute-based watermarking is both effective and practical. --- ### Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study Authors: Qiming Bao, Sherry J. H. Feng, Kim Chester Eugenio, Meng Fon Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03172v3 Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S.", not (NAME) -- so that clinical text stays fluent and downstream tools keep working. But this only helps if the substitution does not itself corrupt the signal those tools rely on. We ask a narrow, testable question: on the spans a de-identifier actually masks, can downstream PHI detectors still find the surrogate? We introduce a paired, multi-detector evaluation protocol that (i) scores utility only on masked spans, decoupling coverage from utility; (ii) uses equivalence testing (TOST) rather than null-hypothesis significance testing, which is uninformative at our sample size (57k paired spans); and (iii) builds a surrogate-failure typology separating fixable generator defects from intrinsic detector limits. Across 11 detectors, 7 benchmarks, and 7 languages (1,750 documents), recall on masked spans moves from 76.1% to 74.9% -- a change our equivalence test shows is statistically equivalent to zero within a +/-2-point margin (p ~ 3e-9), with detector ranking preserved. The residual loss does not reflect detectors getting worse at PHI: it concentrates in malformed and out-of-distribution surrogates (truncation Chicago -> Illino, salience loss Cedars-Sinai -> Vidant). A redaction floor and an open-source surrogate baseline indicate the effect is a property of well-formed substitution, not of one tool. We release the evaluation subsets, scoring code, and an interactive dashboard at https://custodianai.pages.dev so the protocol can audit any structure-preserving transform. --- ### Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study Authors: Qiming Bao, Sherry J. H. Feng, Kim Chester Eugenio, Meng Fon Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03172v2 Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S.", not (NAME) -- so that clinical text stays fluent and downstream tools keep working. But this only helps if the substitution does not itself corrupt the signal those tools rely on. We ask a narrow, testable question: on the spans a de-identifier actually masks, can downstream PHI detectors still find the surrogate? We introduce a paired, multi-detector evaluation protocol that (i) scores utility only on masked spans, decoupling coverage from utility; (ii) uses equivalence testing (TOST) rather than null-hypothesis significance testing, which is uninformative at our sample size (57k paired spans); and (iii) builds a surrogate-failure typology separating fixable generator defects from intrinsic detector limits. Across 11 detectors, 7 benchmarks, and 7 languages (1,750 documents), recall on masked spans moves from 76.1% to 74.9% -- a change our equivalence test shows is statistically equivalent to zero within a +/-2-point margin (p ~ 3e-9), with detector ranking preserved. The residual loss does not reflect detectors getting worse at PHI: it concentrates in malformed and out-of-distribution surrogates (truncation Chicago -> Illino, salience loss Cedars-Sinai -> Vidant). A redaction floor and an open-source surrogate baseline indicate the effect is a property of well-formed substitution, not of one tool. We release the evaluation subsets, scoring code, and an interactive dashboard at https://custodianai.pages.dev so the protocol can audit any structure-preserving transform. --- ### EFX Allocation In (Multi)Hypergraphs Authors: Thanasis Lianeas, Alkmini Sgouritsa, Minas Marios Sotiriou Published: 2026-08-04 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2608.03171v1 We study fair allocations of indivisible goods among agents with heterogeneous monotone valuations. As fair we consider the allocations that are envy-free-up-to-any-good (EFX). Finding if EFX alloca- tions always exist, even for agents with additive valuations, is a major open problem in Fair Division. Christodoulou et al. (2023) introduced the (multi-hyper)graph setting, where agents and goods are represented by vertices and edges of a graph, respectively, and only the endpoints of an edge may have non-zero marginal value for it. We show that for hypergraphs with girth at least 4 and agents with general monotone valuations there always exists an EFX allocation and can be constructed in polynomial time. We generalize our approach to also show that multi-hypergraphs with girth (on the simple hypergraph) at least 4 always admit an EFX allocation, as long as there exists a single vertex whose incident edges have multiplicity at most the size of that edge minus 2; our construction in this case needs pseudo-polynomial time. --- ### Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation Authors: Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi, Ravisha De Alwis Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03166v1 Role-Playing Language Agents (RPLAs) are increasingly deployed in high-stakes applications such as healthcare assistance, customer support, and education, where maintaining consistent personas, ethical constraints, and behavioral coherence under adversarial pressure is critical. Existing evaluation approaches rely on static benchmarks or isolated single-turn prompts that fail to capture cumulative behavioral failures emerging over extended interactions. We present a modular multi-agent platform for adversarially stress-testing RPLAs through structured, multi-turn dialogue. The system coordinates three agents: a strategy-driven Interrogator Agent that applies six progressive adversarial strategies, a Target Agent representing the RPLA under evaluation, and an automated Judging Agent that scores behavior across role fidelity, drift, ethical deviation, and consistency dimensions. Through experiments across three personas and three LLM families, we demonstrate that multi-strategy adversarial evaluation reveals failure modes invisible to single-strategy testing, reducing overall robustness scores by 0.17--0.20 points on average. Cross-model validation confirms consistent degradation patterns across Llama-3.3-70B, GPT-4o-mini, and Claude-3.5-Haiku, with Authority Challenge and Emotional Manipulation emerging as the most effective attack strategies. Automated judging achieves strong human alignment ($r = 0.82$, Fleiss' $κ= 0.71$). This work is released as an open-source platform to support AI safety and reproducible RPLA benchmarking. While the framework enables systematic discovery of failure modes, we acknowledge potential ethical risks associated with adversarial testing methodologies and emphasize responsible usage for improving AI safety. --- ### SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding Authors: Wei Song, Yuxin Cao, Zhenchang Xing, Liming Zhu, Jin Song Dong, Yulei Sui, Jingling Xue Published: 2026-08-04 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2608.03165v2 Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortions but also deliberate removal. We revisit spread-spectrum embedding, a classical watermarking principle, inside a modern neural post-hoc watermarking architecture. Our starting point is a measurement: in existing encoder-decoder schemes each message bit occupies only a small fraction of the image, a shared contributing factor to their fragility, since removal then need only disturb the region a bit occupies. SpreadMark instead spreads each bit as a dense pseudo-random codeword over the whole image and recovers it by matched-filtering a learned cover-suppressed chip representation, with a parallel convolutional decoding path and sparsification-aware training. A conditional chip-space analysis shows that, under a codeword-independent perturbation model, dense spreading increases the budget required to disrupt matched-filter recovery. Evaluated on COCO and DIV2K against nine schemes, SpreadMark is the only evaluated method retaining high detection under both the regeneration and the latent-space sparsification settings we test, with competitive JPEG and additive-noise robustness. It keeps the embedded watermark imperceptible, maintaining high perceptual quality on both COCO and DIV2K. --- ### SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding Authors: Wei Song, Yuxin Cao, Zhenchang Xing, Liming Zhu, Jin Song Dong, Yulei Sui, Jingling Xue Published: 2026-08-04 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2608.03165v1 Invisible image watermarks are increasingly used for deepfake detection and provenance tracking, where they must survive not only incidental distortions but also deliberate removal. We revisit spread-spectrum embedding, a classical watermarking principle, inside a modern neural post-hoc watermarking architecture. Our starting point is a measurement: in existing encoder-decoder schemes each message bit occupies only a small fraction of the image, a shared contributing factor to their fragility, since removal then need only disturb the region a bit occupies. SpreadMark instead spreads each bit as a dense pseudo-random codeword over the whole image and recovers it by matched-filtering a learned cover-suppressed chip representation, with a parallel convolutional decoding path and sparsification-aware training. A conditional chip-space analysis shows that, under a codeword-independent perturbation model, dense spreading increases the budget required to disrupt matched-filter recovery. Evaluated on COCO and DIV2K against nine schemes, SpreadMark is the only evaluated method retaining high detection under both the regeneration and the latent-space sparsification settings we test, with competitive JPEG and additive-noise robustness. It keeps the embedded watermark imperceptible, maintaining high perceptual quality on both COCO and DIV2K. --- ### Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational Reasoning Authors: Sahil Al Farib, Momota Ahsana Meem, Sheikh Redwanul Islam, Md. Tanvir Raihan Published: 2026-08-04 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.03161v1 Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not fully preserve. This paper presents an evidence-grounded multimodal pipeline that transcribes lectures, selects semantic anchors, applies optical character recognition (OCR), and uses a vision-language model to extract only concepts and typed relationships supported by transcript, OCR, or visual evidence. Mentions are validated and canonicalized into a provenance-rich knowledge graph. On three neural-network lectures, the pipeline processed 3,118 frames, 756 transcript segments, and 559 anchors. It retained 1,022 concept and 312 relationship mentions, yielding 172 canonical concepts and 282 relationships with 90.38% endpoint coverage. A preliminary three question retrieval test achieved 100% top-1 and top-3 accuracy and 100% mean top-5 recall. The contribution is an auditable construction method rather than a state-of-the-art performance claim. --- ### Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models Authors: Yuxin Cao, Wei Song, Jingling Xue, Jin Song Dong Published: 2026-08-04 Categories: cs.MM, cs.CV arXiv: https://arxiv.org/abs/2608.03160v2 When asked which of two events came first, video large language models can fail in two opposite ways: cave to a false claim, or reject a true one. Prior video sycophancy work measures only the first and mitigates it by teaching the model to trust the user less, a fix known in text and image models to worsen the second. In video, both failures come from two causes the literature treats as one: availability, whether the sparse sampled frames contain the two events, and weighting, whether that evidence is trusted over the user. We separate them with two interventions that keep the claim fixed: a frame-preserving reorder that flips the claim's truth, and a sampling-offset shift that captures or misses both events at a fixed frame budget. When the events are missed, the two twins present identical frames, so each of the nine models we evaluate accepts a true and a false claim at the same rate, making Youden's $J=0$ by construction. Availability is necessary but not sufficient. Five of the nine read the order, yet four of those five still cave to the false claim, so their deference hits a weighting ceiling. Since trust cannot be calibrated over evidence that was never sampled, we propose a reversal test that cancels the model's order prior by scoring the sampled frames forward and reversed, then answers, resamples, or abstains without reading the claim. The test raises the order accuracy to 0.92-1.00 on the models that read the order and abstains rather than guesses on those that cannot. --- ### Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models Authors: Yuxin Cao, Wei Song, Jingling Xue, Jin Song Dong Published: 2026-08-04 Categories: cs.MM, cs.CV arXiv: https://arxiv.org/abs/2608.03160v1 When asked which of two events came first, video large language models can fail in two opposite ways: cave to a false claim, or reject a true one. Prior video sycophancy work measures only the first and mitigates it by teaching the model to trust the user less, a fix known in text and image models to worsen the second. In video, both failures come from two causes the literature treats as one: availability, whether the sparse sampled frames contain the two events, and weighting, whether that evidence is trusted over the user. We separate them with two interventions that keep the claim fixed: a frame-preserving reorder that flips the claim's truth, and a sampling-offset shift that captures or misses both events at a fixed frame budget. When the events are missed, the two twins present identical frames, so each of the nine models we evaluate accepts a true and a false claim at the same rate, making Youden's $J=0$ by construction. Availability is necessary but not sufficient. Five of the nine read the order, yet four of those five still cave to the false claim, so their deference hits a weighting ceiling. Since trust cannot be calibrated over evidence that was never sampled, we propose a reversal test that cancels the model's order prior by scoring the sampled frames forward and reversed, then answers, resamples, or abstains without reading the claim. The test raises the order accuracy to 0.92-1.00 on the models that read the order and abstains rather than guesses on those that cannot. --- ### Surface Keypoint Representation for Multi-Object and Articulated Human-Object Interaction Generation Authors: Xiaogang Peng, Zeyu Han, Zichong Meng, Yiming Xie, Jihua Zhu, Gang Hua, Huaizu Jiang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03158v1 Daily activities require humans to coordinate whole-body motion with the motion of surrounding objects. Despite recent progress in human-object interaction (HOI) generation, most existing methods assume interactions with a single rigid object and do not extend well to scenarios involving a variable number of objects or articulated objects with diverse joint mechanisms. We propose surface keypoint trajectories as an object motion representation: for each rigid component, whether a standalone object or one part of an articulated assembly, we track a small set of non-collinear surface points over time. This representation handles multi-object coordination and diverse articulation mechanisms directly from point dynamics without requiring explicit joint-type specification. To model when and where each body region contacts each object, we introduce a spatio-temporal contact distance field that extends distance-based contact modeling to whole-body, multi-object, and articulated settings. We factorize HOI generation into three stages: generating object motions from text or waypoints, predicting the contact distance field, and synthesizing whole-body motion with contact-guided optimization. Experiments on ParaHome, HIMO, ARCTIC, and OMOMO demonstrate better or comparable performance to existing methods across single-object, multi-object, and articulated interaction settings. --- ### ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction Authors: Shufan Ming, Yikun Han, Gibong Hong, Rui Zhang, Halil Kilicoglu Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03154v1 Biomedical relation extraction (BioRE) extracts structured knowledge from biomedical literature for applications such as knowledge base construction and hypothesis generation. Traditional symbolic systems such as SemRep provide high precision but limited recall, while large language models (LLMs) offer stronger contextual reasoning but remain prone to false-positive predictions. We developed ANCHOR-RE, a framework that integrates ontology-guided reasoning, external knowledge grounding, and data-driven verification rules into LLM inference. We evaluated it on three BioRE benchmarks (SemRepGS, DDI, and ChemProt) using both proprietary and open-weight LLMs. To assess generalizability beyond benchmark datasets while reducing potential evaluation bias from LLM pretraining contamination, we conducted a temporal evaluation using 100 biomedical articles published in 2026. With the proprietary backbone, ANCHOR-RE outperformed direct LLM prompting, improving micro-F1 from 0.654 to 0.676 on SemRepGS, from 0.769 to 0.872 on DDI, and from 0.939 to 0.941 on ChemProt. On DDI and ChemProt, it also outperformed previously reported inference-only methods and approached fine-tuned or instruction-tuned systems without parameter updates. Similar performance gains observed with open-weight LLMs indicate that the benefits were not limited to the proprietary backbone. On the post-cutoff set, manual assessment of 500 randomly sampled predictions yielded a precision of 69%, maintaining consistent precision on previously unseen biomedical literature. Neuro-symbolic reasoning can improve the reliability of LLM-based BioRE without fine-tuning. Results across multiple benchmarks, model families, and post-cutoff literature support ANCHOR-RE as a practical training-free approach to biomedical literature mining. --- ### UniGD: A Unified Generative-Discriminative Framework for Industrial Retrieval Authors: Shujie Ji, Yawei Kong, Yilin Zhao, Li Wang, Xialong Liu, Peng Jiang Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03150v1 Generative retrieval (GR) is a promising paradigm for industrial search advertising, yet its deployment is constrained by strict relevance and latency requirements. Existing systems cascade GR with an independent relevance model, decoupling the generative likelihood objective from query-ad relevance discrimination, which compromises effectiveness and increases serving costs. We propose a Unified Generative-Discriminative framework (UniGD) that integrates retrieval and relevance scoring within a single model. To mitigate gradient interference in joint optimization, UniGD introduces Conflict-Aware Gradient Enhancement (CAGE) to adaptively coordinate the two objectives. UniGD further designs a Codebook-Anchored Representation Module (CAM) that anchors item representations to frozen hierarchical codebooks distilled from a multimodal pretrained model, thereby endowing them with rich and generalizable semantic priors. For heterogeneous short-video, product, and live-stream ads, UniGD proposes Heterogeneous Ad-material Modeling (HAM), which captures cross-type semantic commonality over a shared backbone while preserving type-specific modeling capacity. Online AB tests on Kuaishou search advertising platform show that UniGD raises ad revenue by 5.78%, reduces inference latency by 33%, and improves discriminative relevance estimation. On NQ320K and MS300K, UniGD improves Recall@10 over the strongest reproduced GR baseline by 8.44% and 3.19%, respectively. --- ### Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation Authors: Sicong Chang, Yidan Shen, Wen Yu, Jiefu Chen, Xin Fu, Renjie Hu Published: 2026-08-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.03148v1 RAG improves the factual grounding of LLM by incorporating external knowledge, but deploying RAG on mobile and edge devices remains challenging because retrieved context increases computation and memory. A direct way to reduce this cost is to retain only one retrieved chunk before generation, but the top-ranked retrieved chunk is not always the most evidence-supporting one, since retrieval similarity does not necessarily imply evidential sufficiency. Existing context-reduction methods can improve context quality, but often require additional LLMs or compressors that are costly under a strict mobile budget. In this paper, we study lightweight RAG chunk selection as an evidence-alignment problem. Our selector combines three complementary feature sources: question hidden states that represent LLM-side query intent, MoE routing-derived expert signals that capture the generator's internal routing structure, and retrieved chunk embeddings that preserve candidate-side evidence geometry. A compact multilayer perceptron maps these features to an evidence prototype in the chunk embedding space, and the candidate most aligned with this prototype is selected by cosine similarity. For stricter deployment budgets, we further introduce an optional task-aware feature selection strategy to reduce the selector input dimension. To support supervised evaluation, we construct semantic chunk-correctness labels based on evidence sufficiency rather than answer-string containment. Experiments show that the proposed selector consistently improves rank-1 evidence selection over mobile-applicable baselines by an average of 2.5%. These results suggest that using LLM-side query representations and MoE routing information and aligning them with retrieval-side candidate embedding is an effective and parameter-efficient strategy for mobile-applicable RAG chunk selection. --- ### CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation Authors: Tingzhang Luo, Ruizhong Liu, Yichao Liu, Cheng Fan, Yu Liu, Jianyuan Guo Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03147v2 Referring Remote Sensing Image Segmentation (RRSIS) has achieved significant progress through the integration of VLMs and the Segment Anything Model (SAM). However, this progress largely relies on strong pre-trained capabilities, while leaving two fundamental limitations insufficiently addressed: (1) Architectural Weak-Coupling, where the unidirectional flow forces reliance on coarse VLM prompts and wastes SAM's pixel-level structural guidance, causing localization drift; and (2) Object-Centric Semantic Bias, where models overemphasize dominant object semantics while remaining insensitive to spatial reasoning crucial for RRSIS. Motivated by these observations, we propose CROSS, a tightly integrated paradigm for RRSIS. First, we introduce Linguistic-Guided Cascaded Distillation (LGCD) to bridge the architectural gap, which distills SAM's geometric affinities as soft regularizers into VLM intermediate layers, injecting dense structural priors to refine localization. Second, Perspective-Spatial Contrastive Learning (PSCL) imposes cross-anchored constraints by mining mask-filtered deceptive distractors and spatial-linguistic counterfactuals as hard negatives, explicitly shattering semantic shortcuts to enforce genuine logical consistency. Extensive experiments on RRSIS benchmarks demonstrate that CROSS achieves state-of-the-art performance and maintains precise localization even under severe spatial description perturbations, standing as a robust new paradigm for RRSIS. --- ### Spatial proteomics guided by H&E-based AI reveals recurrence-risk niches in triple-negative breast cancer Authors: Yesung Cho, Ji Hwan Park, Chanil Kim, Hyewon Kim, Honglan Li, Yumin Lee, Geongyu Lee, Sujeong Hong, Seong Min Park, Yoonyoung Lee, Hee Sool Rho, Sumin Lee et al. Published: 2026-08-04 Categories: cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2608.03145v1 Deep learning models can predict cancer recurrence from H&E stained slides, but the localized molecular states underlying these predictions remain largely obscured. Here, we developed an outcome informed spatial pathology framework in TNBC that integrates AI generated recurrence risk heatmaps with mass spectrometry based spatial proteomics. In a cohort of 156 patients, distribution based aggregation of high scoring patches achieved an AUC of 0.77 and a C-index of 0.77 in an independent test cohort. Bulk proteomics associated high image derived risk with cell cycle and genome maintenance programs and low risk with immune activation. High and low risk patches coexisted within the same tumor compartment and displayed distinct nuclear and architectural features, revealing intratumoral heterogeneity beyond tissue compartment identity. We then used the heatmaps as coordinate level guides to physically isolate and profile 46 AI defined tumor regions from two recurrence patients. Spatial proteomic profiling revealed a concordant molecular contrast across both patients: mitotic programs were enriched in high risk regions and immune and antigen presentation programs in low risk regions. A 13 protein composite derived from these spatial contrasts showed a trend toward poorer recurrence-free survival with increasing scores in an expanded cohort, while the corresponding transcript based composite stratified recurrence free survival in the independent METABRIC TNBC cohort. Integrating the protein composite with the H&E derived risk score improved the out of bag C-index from 0.679 to 0.739 and enhanced time dependent discrimination at 3 and 5 years. Together, these findings define a new role for outcome trained AI models as spatially explicit experimental guides that connect prognostic morphology with localized molecular states and advance biologically grounded, multiscale biomarker discovery in TNBC. --- ### From Routes to Steps: Separating Semantic Progress from Local Execution in Vision-and-Language Navigation Authors: Xiangyun Huang, Xiangchen Wang, Runfeng Lin, Yihao Xu, Kangyu Huang, Jiang Hengchen, Xiwang Dong, Lin Jiarong Published: 2026-08-04 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.03143v1 Vision-and-Language Navigation (VLN) requires an agent to follow a route-level instruction by executing its constituent steps from egocentric visual observations. Existing VLM-based navigators typically supervise both capabilities through next-action prediction alone, making progress-tracking errors difficult to distinguish from execution errors. When an agent deviates from the route, a corrective action label may recover the next movement but does not indicate whether the agent selected the wrong sub-instruction or failed to execute the correct one. Consequently, the agent may continue making decisions from an erroneous progress state. To resolve this ambiguity, we propose \textbf{Route2Step}, a framework that decouples semantic progress tracking from action generation through an explicit step-level interface. The Instruction Analysis Module ($\mathcal{M}_{\mathrm{IA}}$) predicts this state from the global instruction and visual history. Conditioned on the predicted state and recent observations, the Action Generation Module ($\mathcal{M}_{\mathrm{AG}}$) generates local action chunks. To supervise the progress state without manual temporal labels, E-SPA, a step-alignment procedure, associates sub-instructions with their corresponding portions of route-level demonstrations. These alignments enable state supervision for incorrect progress estimates, while direct action supervision is reserved for rollout groups that repeatedly fail under the correct active sub-instruction. On R2R-CE, Route2Step improves SR from 48.1\% to 55.3\% and SPL from 43.3\% to 48.2\%, using 190K state-level corrective samples while requiring only 11.5K directly action-supervised states. Experiments in real-world indoor and outdoor environments further demonstrate the practical applicability of Route2Step. The project page is: https://sisyphus-hxy.github.io/Route2Step/. --- ### Minimax-Optimal Semiparametric Contextual Dynamic Pricing with Multimodal Revenue Authors: Xueping Gong, Zhuoluo Zhang, Zhaowei Miao, Jiheng Zhang Published: 2026-08-04 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.03142v1 We study contextual dynamic pricing with arbitrary covariate sequences and bounded, possibly nonbinary purchase quantities. Demand follows a semiparametric surplus-index model with an unknown linear valuation parameter and an unknown Hölder-smooth response. We impose neither concavity nor strong unimodality on revenue and allow nonunique optimal prices. We develop a pilot-corrected layered decision-partitioning policy that combines directional pilot estimation, local polynomial learning, predictable data assignment, and global action elimination. Pilot correction removes the first-order effect of valuation-parameter error, while permanent labels enable concentration under adaptive sampling. The policy attains the minimax smoothness-dependent horizon rate up to logarithmic factors; a matching lower bound already holds for a constant-context binary-demand subclass. --- ### Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning Authors: Meicong Zhang, Tiancheng Su, Jiahao Cheng, Guoxiu He, Xinqi Tao, Dejia Song Published: 2026-08-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.03138v1 Generating a rigorous paper introduction with large language models (LLMs) remains challenging, since it requires coordinating background, gap identification, method and contribution within a coherent narrative. Existing solutions externalize this process as multi-stage prompts or agent workflows which are expensive and vulnerable to cross-stage drift. We propose StructPO, a struct-aware policy learning framework that internalizes the entire multi-stage writing workflow into a single-pass policy controlled by explicit stage tokens. StructPO introduces struct-aware credit assignment to decouple local stage quality from global coherence and refinement-guided optimization to internalize revision behavior into the first-pass policy. Experiments show that StructPO improves semantic alignment, structural rationality and inference efficiency over workflow-based baselines, generalizes to out-of-domain settings, and remains competitive with GPT-5.1 in human evaluation when scaled to Qwen3-32B. These results show that internalizing academic writing workflows through fine-grained policy optimization offers a viable alternative to costly external orchestration. --- ### Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents Authors: Xiaolong Sun, Qichao Wang, Hangyu Li, Liang Chen Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03137v1 Large language model (LLM) agents must retain reusable information, control a bounded active context, and recover earlier evidence during long-horizon interaction. Existing methods commonly optimize long-term memory (LTM) and short-term memory (STM) separately, while unified policies are often trained primarily with trajectory-level feedback, which provides weak credit for individual memory decisions. We present Verifiable Memory (VerMem), a framework that represents LTM, active context, and episodic history as distinct states and controls them with one memory operation policy. Seven atomic operations let the policy add, revise, or soft-delete LTM entries; retrieve LTM into the active context; filter or summarize the active context; and restore selected episodic fragments. VerMem is initialized by supervised fine-tuning and trained with a three-stage reinforcement-learning curriculum. The local verifier scores executable memory transitions, and a global verifier assesses evidence coherence and terminal-memory consistency after task completion. These scores are combined with programmatically computed task, evidence-recall, efficiency, and constraint signals through hierarchical credit assignment. The verifiers are used only during training. Across five benchmarks and two LLM backbones, VerMem achieves the best result on the vast majority of reported metrics and consistently outperforms strong memory baselines. Under controlled online-token budgets on three interactive benchmarks, it also achieves the strongest efficiency--performance frontier among the compared methods. Code is available at https://github.com/Sun-SYSU-24/VerMem. --- ### Frozen High-Resolution Inference for Cross-City Object Detection: An AI City Challenge 2026 Study Authors: Jaeuk Kim Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03136v1 Cross-city object detection requires a detector trained in one city to generalize to an unlabeled target city. In AI City Challenge 2026 Track 6, we analyze archived configurations of a single RF-DETR-Large detector inside an air-gapped Training-as-a-Service platform whose server returns only an aggregate COCO-style AP over a hidden mixture of source- and target-city images. Frozen 1120 x 1120 inference of a checkpoint trained at 704 x 704 achieved the highest aggregate AP among the evaluated configurations (0.3272 -> 0.3654, +0.0382) without any parameter update, with the largest relative gain on small objects and the largest absolute gain on medium objects, at 2.53x the input pixels. A warm-start 1120px fine-tuning recipe reached 0.3470 while its in-domain validation AP rose (0.767 -> 0.789), a caution that in-domain validation is an unreliable model-selection signal under aggregate-only cross-city feedback. Because that run's evaluation used a higher confidence threshold than the inference-only runs (0.05 vs. 0.01), we treat its score as a descriptive archived outcome rather than a controlled verdict on fine-tuning. Gray-world normalization did not meaningfully change the frozen-1120 result, and a rectangular run was found by audit to have used an unintended portrait orientation. We release verbatim platform commands, configuration snapshots, and an explicit evidence boundary for every claim. Each configuration was submitted once and the best was selected on the hidden server, so these are exploratory, audited findings about the aggregate mixture; they do not establish target-city-specific improvement. --- ### Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds Authors: Ning Zhu, An Chen, Mengfei Zhao, Juntao Xu, Jingze Liang, Boyuan Gu, Liang-Jian Deng Published: 2026-08-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.03135v1 Text-to-image diffusion models can generate individual concepts well, but they often omit or merge concepts incorrectly with multiple concepts. We trace these failures to an early coordination bottleneck: before denoising begins, prompt-conditioned attention may allocate different concepts to strongly overlapping spatial support, which can keep their attention coupled as denoising proceeds. This observation motivates treating compositional generation as a boundary-condition problem rather than repeatedly controlling the evolving trajectory. To this end, we propose Rectify-then-Diffuse (RTD), a training-free framework that rectifies the initial allocation once before standard denoising. Firstly, we propose Soft-Overlap Disentanglement (SOD), which converts normalized overlap between pilot concept maps into a differentiable and layout-agnostic separation objective. Secondly, we introduce Isotropic Gradient Rectification (IGR), which normalizes the SOD gradient and applies a bounded latent displacement with a consistent scale across prompts and initializations. Extensive experiments show that RTD achieves state-of-the-art compositional fidelity and robust gains. On the AE-Bench object pair subset, RTD improves BLIP-VQA by 45.8% and ImageReward by 19.6% over CO3 while running 2.3$\times$ faster. Code will be released at https://github.com/Z-yiwei/rectify-then-diffuse --- ### DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents Authors: Jong Wook Kim, Byoungjae Min, Kennedy Edemacu, Yoonhyuk Choi, Sae-Hong Cho, Beakcheol Jang Published: 2026-08-04 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.03130v1 Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly. We formalize this threat as adaptive transcript privacy and introduce DP-MemView, a differentially private interface that privately selects public response-conditioning views and exposes those views---rather than raw memory---to the response LLM. Each private selection is charged to every protected attribute whose memory group intersects the read set. Per-attribute ledgers block any selection that would exceed its cap and return a fixed generic view instead. Under an explicit interface contract, we prove pure B_a-DP for the entire adaptive transcript. We also extend the result to stores that differ across multiple protected groups and bound how much observing the transcript can change an adversary's prior odds. We evaluate the online and preallocated modes with three response LLMs on a controlled adjacent-store benchmark and a public-corpus transfer track. Both modes keep transcript distinguishability near chance while preserving target-required personalization and overall response quality. Further diagnostics show that removing key safeguards causes mismatched output support, missing ledger charges, revealing side channels, or growing long-horizon leakage. --- ### Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search Authors: Qinglong Hu, Qingfu Zhang, Fei Liu, Xialiang Tong, Kun Mao, Mingxuan Yuan Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03129v1 Large Language Model-assisted Evolutionary Search (LES) has emerged as a powerful paradigm for automated algorithm design. However, existing LES methods primarily optimize for average performance, inherently directing search effort toward instances that contribute most to this metric while leaving others poorly served, resulting in weak tail robustness and limited real-world reliability. To address this limitation, we propose Dynamic Instance Clustering and Specialized Algorithm Design (DyCA), an LES framework with a feature-free, structure-aware mechanism for constructing reliable algorithm portfolios under heterogeneous instance distributions. DyCA treats instance clustering as a co-evolving component within the search process, reusing accumulated evaluation data as feature-free signals to progressively partition instances with similar algorithmic response patterns. The uncovered clusters decompose the mixed objective into a set of structure-aware sub-objectives, thereby enabling finer-grained and more adaptive guidance for specialized algorithm design. Experimental results across four algorithm design tasks with heterogeneous instances demonstrate that DyCA outperforms state-of-the-art LES baselines, improving tail robustness by an average of 15.2\% and overall performance by 7.1\% while maintaining competitive head performance. --- ### DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units Authors: Haoyu Gu, Haotian Lu, Jingrun Du, Xiao-Ping Zhang Published: 2026-08-04 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.03127v1 Hand motion carries the finest-grained information in human activity, yet the representations behind hand generation, understanding, and robot learning are overwhelmingly continuous--joint angles or MANO parameters. These are accurate but unstructured: a finger cannot be indexed or edited as a symbol, and nothing marks a pose as anatomically valid. Discrete symbolic representations supply exactly this structure, and Hand Labanotation (HL) has shown they are feasible for the hand, writing motion as a T x 40 grid of one fixed direction symbol per bone. Building on this grid, we ask the question underneath it: the anatomical unit a symbol should span--bone, finger, or whole hand. DigitCode answers it by adapting, grouping, and layering HL's alphabet along the hand's unit hierarchy within one code, cutting the symbolic representation's quantization error by three quarters. The lever is the unit, not the quantizer family: at a fixed unit, training-free and learned strong quantizers are interchangeable on reconstruction, while moving down the anatomical hierarchy is what shifts accuracy. The hierarchy also tracks what downstream tasks need. Because a finger is a genuine, enumerable unit, one per-finger token doubles as a training-free, editable handle for jobs a continuous representation cannot address--repairing malformed generated hands, and retargeting them onto robots. We release HandTok, a reproducible testbed, so hand tokenizers can be compared unit-for-unit. Project page: https://digitcode-demo.github.io. --- ### Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning Authors: Zezheng Wu, Xinghe Cheng, Qinggang Zhang, Haoran Luo, Jiapu Wang, Qing Yang, Jingwei Zhang Published: 2026-08-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.03123v1 Machine unlearning aims to eliminate the influence of sensitive data on a model. In the real world, unlearning requests arrive continually, which gives rise to two challenges. First, an unlearning intervention may redistribute target-related computation across remaining pathways, allowing previously forgotten knowledge to re-emerge. Second, repeated unlearning interventions may progressively reduce the model capacity needed to preserve retained utility. To address these challenges, we propose the Trajectory-guided Forget-Recover Network (TFR-Net). TFR-Net tracks channel-level risk across requests. It separates persistent target-related channels from transient hotspots and suppresses only the persistent ones. TFR-Net also recovers model capacity by reactivating dormant channels. These channels make strong contributions to retained utility and show low current and historical forget risk. The recovery is accepted only when retained-utility degradation remains within a predefined tolerance. Experiments on four datasets show that TFR-Net consistently achieves a more favorable trade-off between unlearning effectiveness and retained utility than representative baselines. --- ### SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval Authors: Long Hoang Dang, Tuan Nguyen Huu, Nguyen Minh Hieu, Tu Minh Phuong Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03120v1 Adapting CLIP for zero-shot sketch-based image retrieval (ZS-SBIR) via prompt learning faces a fundamental tension: the model must bridge the sketch-photo domain gap through task-specific adaptation, yet the added flexibility risks overfitting to seen training categories and eroding CLIP's zero-shot generalization. We present SeCo-SBIR, a semantically consistent prompt learning framework that resolves this tension from both sides. First, a text-guided multi-modal prompting strategy routes learnable prompt vectors through CLIP's text encoder and projects the resulting intermediate representations into the visual encoder at every layer via learnable coupling functions. Because the text encoder has already learned robust, abstract category-level semantics from large-scale language supervision, this mechanism injects transferable semantic knowledge directly into the visual pathway - adapting the model to the sketch-photo domain while inherently favoring generalization to unseen classes. Second, a perturbation-based consistency constraint addresses the residual overfitting risk from the learnable coupling functions by aligning the adapted model with a frozen CLIP reference branch using an asymmetric InfoNCE objective - augmented inputs feed the frozen branch while clean inputs feed the trainable branch - anchoring the learned representations to CLIP's generalizable feature space. Together with lightweight adapters and a multi-objective loss combining triplet, NT-Xent, and classification terms, SeCo-SBIR achieves state-of-the-art results on all three standard ZS-SBIR benchmarks across categorical, generalized, and across-dataset settings. --- ### Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR Authors: Yongshi Ye, Liang Zhang, Yidong Chen, Xiaodong Shi, Biao Fu Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.03119v1 Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning but typically relies on ground-truth (GT) answers, limiting scalability. Voting-based label-free RLVR replace gold supervision with answer-level consensus from model samples. However, collapse arises when the same answer-level signal is used both to estimate rewards and to drive token-level policy optimization, encouraging the model to directly reinforce answer tokens rather than improve reasoning. We propose OM-GRPO, a label-free RLVR framework that decouples reward estimation from policy optimization. OM-GRPO masks gradients on the answer span while retaining answer-level rewards through a soft consensus signal, shifting optimization pressure away from answer tokens. We further introduce Contrast-Augmented Reward, which refines reward estimation via low-cost pairwise comparisons over existing trajectories without additional rollouts. Across diverse reasoning benchmarks and three LLM backbones, OM-GRPO consistently outperforms existing label-free RLVR methods and matches supervised GT-reward training with stable optimization. This stability is particularly beneficial in the Test-Time Training setting, where OM-GRPO surpasses majority voting by 4.24 points. --- ### From SQL Errors to Concept Gaps: An AI-Powered Knowledge Graph Analytics Platform for Personalized Feedback Authors: Abdulrahman AlRabah, Weijian Zhou, Xing Gao, Abdussalam Alawini Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03118v1 This innovative practice full paper describes an AI-powered knowledge graph platform that connects SQL errors to conceptual gaps in undergraduate and graduate database systems courses. Students learning Structured Query Language (SQL) frequently struggle with semantic errors that reflect conceptual misunderstandings rather than syntax mistakes. A query may execute yet return incorrect results due to gaps spanning related concepts; misusing NATURAL JOIN in place of an explicit subquery reflects intertwined misunderstandings of JOIN, GROUP BY, and HAVING. Autograding systems detect correctness but provide surface-level feedback without connecting errors to the conceptual structure of the course. Educational knowledge graph research has shown the value of structured concept representations for curriculum analysis and adaptive learning, but these approaches have not been applied to diagnosing SQL misconceptions from student submissions. We present a platform that automatically extracts course concepts and relations from instructional materials, links them to student submission traces through a graph database, and classifies errors at the concept level. We evaluate the platform across two database systems courses at two universities, one using real student submissions and one using simulated submissions, through an expert study with five participants and an automated evaluation using an LLM as a judge. Results show that 95.7% of extracted nodes were rated as at least somewhat valid and 63.8% of triplets were rated fully correct. Expert feedback confirmed that the generated graphs align with instructor mental models and that mapping errors to course concepts provides actionable diagnostic insight; evaluating impact on student learning remains future work. --- ### Simulation-free and finite-time diffusion model Authors: Kentaro Kaba, Masayuki Ohzeki, Yuki Sughiyama Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.03117v2 The performance of generative diffusion models is determined by the choice of the reference diffusion process connecting the empirical and prior distributions. Conventional approaches typically trade off simulation-free training against finite-time generation. We propose a framework for designing the reference process that achieves both simultaneously. The key idea is to prescribe tractable time-dependent conditional distributions and then construct the reference process realizing them as its marginals. This framework reveals that score matching is not fundamental to diffusion-model training but instead emerges naturally through reversal of the reference process. We further show that conditional flow matching arises as the small-noise limit of the proposed framework. --- ### Simulation-free and finite-time diffusion model Authors: Kentaro Kaba, Masayuki Ohzeki, Yuki Sughiyama Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.03117v1 The performance of generative diffusion models is determined by the choice of the reference diffusion process connecting the empirical and prior distributions. Conventional approaches typically trade off simulation-free training against finite-time generation. We propose a framework for designing the reference process that achieves both simultaneously. The key idea is to prescribe tractable time-dependent conditional distributions and then construct the reference process realizing them as its marginals. This framework reveals that score matching is not fundamental to diffusion-model training but instead emerges naturally through reversal of the reference process. We further show that conditional flow matching arises as the small-noise limit of the proposed framework. --- ### Optimal Liability Design for Medical AI Authors: Rui Mao, Tingliang Huang, Houcai Shen Published: 2026-08-04 Categories: econ.TH, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.03114v1 Artificial intelligence (AI) is increasingly integrated into medical decision-making, yet its liability implications remain complex, particularly when physicians differ in diagnostic skills and their quality is unobservable. This paper develops a principal-agent model in which a social planner designs medical liability to regulate a physician with private quality information who chooses between a standard treatment, a personalized judgment-based treatment, or following an imperfect AI recommendation. Our analysis yields several novel insights. First, we show that the optimal mechanism under asymmetric information is surprisingly simple: a uniform, one-size-fits-all liability level for all physician types who deviate from the standard of care. Despite physician heterogeneity, this simple policy often achieves the full-information first-best outcome, particularly when standard care is reliable or AI is highly accurate. Second, the relationship between AI accuracy and optimal liability is non-monotonic. Contrary to common intuition, better AI does not always imply more relaxed liability. As AI accuracy increases, the optimal liability either decreases monotonically or follows an inverted-U pattern, depending on the uncertainty of the standard treatment. Third, asymmetric information does not universally reduce social welfare. Welfare loss arises only when standard care is unreliable and AI accuracy is too low; even then, its magnitude follows an inverted U-shape, initially increasing as AI complicates the regulatory problem, but declining as more accurate AI helps mitigate it. Finally, we find that information asymmetry is a double-edged sword in the presence of AI, and greater transparency does not benefit all stakeholders equally. --- ### Non-Destructive Quantification of Urea Adulteration in Bovine Milk Using Transmittance Multispectral Imaging Authors: Sharukshan Niranjan, Iresha Ranaweera, Tharindu Chandrarathne, Kalana Dissanayaka, Roshan Godaliyadda, Vijitha Herath, Parakrama Ekanayake, Janak Vidanarachchi Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03113v1 Adulteration of bovine milk using urea remains a major food quality and health concern, motivating the development of rapid and quantitative screening tools. Conventional approaches, including laboratory-based analytical methods and spectroscopic techniques, have been used for urea detection; however, many remain less suitable for rapid, low-cost routine screening due to requirements such as specialized instrumentation, sample preparation, chemical reagents, or laboratory operation. This study introduces a pragmatic, cost-effective, accurate, and laboratory-validated MSI-based method for quantitative urea estimation under controlled density conditions using a multispectral-imaging-based regression framework. An in-house-built multispectral imaging system operating in twelve discrete spectral bands (365--940~nm) was used to acquire multispectral images of milk samples prepared with controlled urea addition and water for density balancing. Fresh milk was obtained on the day of image acquisition, and the specific gravity of the milk was verified to be 1.032 at 20°C using a hydrometer. Multiple linear regression provided an initial mapping with a high validation $R^2$ of 0.9599, while a feed-forward neural network further improved predictive performance with a validation $R^2$ of 0.9773. These results demonstrate the feasibility of transmittance multispectral imaging for accurate, non-destructive urea quantification under controlled density-balanced conditions, supporting its potential as a rapid screening approach for milk-quality assessment. --- ### Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models Authors: Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda Mao Published: 2026-08-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.03112v1 Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications. This challenge is further amplified in video processing, where multiple frames must be analyzed simultaneously. Existing token reduction techniques are largely developed for single-image inputs and therefore fail to account for the temporal and inter-frame redundancies present in video sequences. In addition, these methods generally rely on a fixed, uniform pruning ratio applied across all inputs, which is suboptimal because the degree of redundancy can vary significantly between different videos, necessitating content-dependent pruning levels to preserve critical information. To address these limitations, we propose a two-stage adaptive token pruning strategy specifically designed for video processing. In the first stage, we prune out the redundant frames, and in the second stage, token-level pruning is applied within the retained frames. Crucially, the pruning ratio in the second stage is determined adaptively based on the content of each video. This is achieved by analyzing the correlation structure of token embeddings to quantify redundancy, which is used to determine the ratio. Importantly, our method is entirely post-hoc and requires no additional training or fine-tuning, while achieving strong empirical gains; notably, it improves accuracy by +7\% on a video captioning benchmark at 10\% token retention, while reducing computation TFLOPs by 95\%. --- ### Double Descent in Gradient Boosting Decision Trees via Split-Candidate Scaling Authors: Ryuichi Kanoh Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.03111v1 Double descent is commonly studied by scaling an explicit capacity parameter, such as neural-network width. For gradient boosting decision trees (GBDTs), however, an analogous single-axis capacity parameter has not been established. We propose the number of split candidates as an operational capacity parameter for GBDTs. Holding other training controls fixed, increasing the split-candidate budget refines the feature-quantization grid and expands the dictionary of root-to-leaf paths from which boosting selects its updates. To analyze this expansion, we construct an empirical tree-kernel diagnostic that summarizes how candidate-induced paths group the training examples. A regime in which the empirical kernel rank grows toward the sample size and very small positive eigenvalues emerge exposes noise-sensitive directions; in this regime, test error peaks before decreasing again at larger split-candidate budgets. This perspective predicts that deeper trees should reach the regime with fewer split candidates, larger training sets should require finer grids, and label noise should make the peak more pronounced. Experiments support these predictions and show test-error peaks at intermediate split-candidate budgets across XGBoost, LightGBM, and CatBoost, whereas a random-forest control improves monotonically under the same split-candidate sweep. Taken together, our analysis and experiments support split-candidate scaling as a single-axis capacity intervention for studying GBDTs and suggest that the observed double descent arises from an interaction between candidate-induced geometry and boosting dynamics. --- ### Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language Analysis Authors: Jiakai Lin, Zijun Li, Guoyu Lu Published: 2026-08-04 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.03109v1 Plant root phenotyping is fundamental to understanding below-ground structures, optimizing crop management, and improving agricultural sustainability. This paper presents a multimodal robotic AI framework that integrates 3D skeleton extraction with language-guided reasoning for interpretable and data-efficient root analysis. We develop an unsupervised skeleton extraction network based on Weighted Laplacian Contraction (W-LBC) to generate high-fidelity structural representations from dense point clouds captured by robotic 3D sensing platforms. Quantitative morphological descriptors, including root count, length, branching angle, and density, are computed from the reconstructed skeleton graph to capture geometric and topological characteristics. Building on these features, we introduce an Evidence-First language modeling framework that fine-tunes GPT as an interactive analytical chatbot using automatically generated instruction--response pairs. Each training sample provides measurable evidence before natural-language reasoning, enabling the model to ground interpretation in quantitative morphology. Through supervised fine-tuning, GPT associates numerical structure with semantic meaning, producing biologically consistent explanations of growth patterns and adaptive traits. Experiments show that the structure-guided framework achieves robust, interpretable reasoning across 12 plant species with diverse root architectures. By integrating unsupervised 3D geometric perception with large-scale language understanding, our approach bridges quantitative analysis and semantic interpretation, establishing a unified paradigm for explainable robotic plant root phenotyping. --- ### Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL Authors: Yi Yang, Zhennan Chen, Mingfeng Lv, Hanlei Li, Zhengsen Ruan, Lvqing Yang Published: 2026-08-04 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.03108v1 Offline reinforcement learning (offline RL) can benefit from nearby out-of-distribution (OOD) actions, but estimation errors at these actions may be amplified by bootstrapping. Existing regularization and local-generalization methods control either the admissible OOD region or the influence of generalized targets, often through separate mechanisms. We propose Convex Hull Neighborhood Smooth Dual Generalization (CSDG), which expresses the Bellman backup as an in-sample value target plus a CHN-local correction. This formulation makes the generalized contribution explicit and separates it from the in-sample reference path. The correction is obtained by smoothing in-sample-oriented and OOD-oriented candidates sampled at different perturbation radii. A mixture coefficient lambda scales its contribution to each backup, while the recursive discount remains gamma. Under boundedness and fixed perturbation kernels, we derive an exact one-step correction identity, a time-varying iterate bound, and a fixed-point bound that depends only on the branch discrepancy at the fixed point. We further characterize the implicit policies induced by the idealized operators and give a conditional non-degradation criterion. The practical algorithm approximates these quantities using asymmetric bounded noise and expectile regression, without exact support classification or an additional pessimistic OOD penalty. Experiments on Gym-MuJoCo and AntMaze show strong aggregate performance and stable value estimation. Code is available at: https://github.com/YOUNG-fnxm/CSDG --- ### A Unified Resolution-Conditioned Framework for Orthogonal Line-Scanning Image Fusion Authors: Yiming Gong, Kai Wang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03107v1 Laser line-scanning microscopy enables fast volumetric imaging but produces anisotropic lateral resolution. Orthogonal line scans provide complementary directional information that can recover near-isotropic resolution, yet existing deep-learning methods require a separate model for each optical configuration. We present a unified, resolution-conditioned fusion framework based on Rank Enhanced Linear Attention (RELA). Feature-wise Linear Modulation (FiLM) conditions the network continuously on the resolving-power ratio, enabling one model to adapt across slit widths. We further introduce Adaptive RELA, which replaces fixed-kernel rank enhancement with ratio-conditioned multi-scale depthwise convolutions and uses a learnable attention temperature to adjust selectivity with degradation severity. Training data spanning multiple slit configurations are generated using a physics-grounded separable point-spread-function model verified against measured optical data at 48.3 dB accuracy. The resulting model achieves 34-40 dB PSNR across configurations, whereas unconditioned multi-slit training collapses to 24.3 dB and per-slit specialists lose 4-9 dB outside their training setting. It also generalizes smoothly to unseen intermediate configurations without interpolation artifacts. Ablations show that FiLM resolves configuration ambiguity, global linear attention captures long-range directional correspondences, and adaptive temperature yields an additional 2 dB in the challenging near-isotropic regime, where complementary signals are weak. --- ### FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity Authors: Axi Niu, Zhenguo Wu, Kang Zhang, Qingsen Yan, Jinqiu Sun, Yanning Zhang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03106v1 Infrared image super-resolution (IISR) is important for downstream tasks such as object detection and semantic segmentation. Existing IISR methods often produce artificial textures, over-sharpened edges, and spurious high-frequency details that distort authentic thermal structures and semantic information. To address this issue, we propose FaithIR, a faithful infrared super-resolution framework for reliable machine perception. FaithIR consists of a patch-level conditioning branch that captures global thermal and structural information and a pixel-level restoration branch that performs dense local reconstruction under structural guidance. The entire restoration process is performed directly in the pixel domain to preserve infrared-specific structures and task-relevant information. Extensive experiments on FLIR-IISR, M3FD, and FMB demonstrate strong reconstruction fidelity, cross-dataset generalization, and superior performance in object detection and semantic segmentation. These results show that demonstrate that preserving faithful infrared structure preservations is more important for reliable machine perception than merely pursuing perceptual sharpness alone. --- ### HomoEnsNER: Does Language Alignment Outperform Architectural Complexity in Gujarati Named Entity Recognition? Authors: Chandrakant K. Bhogayata Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03105v3 Named Entity Recognition (NER) for Gujarati remains underexplored, hindered by the absence of capitalization cues, rich morphology, lexical ambiguity, and free word order. Prior ensemble work has emphasized architectural diversity by combining heterogeneous classifiers, multilingual encoders, or classical sequence models, rather than exploiting language-aligned monolingual pretraining. This study asks whether, for a low-resource, morphologically rich language like Gujarati, a homogeneous ensemble of a single monolingual encoder outperforms such architectural diversity. We propose HomoEnsNER, a homogeneous ensemble of five independently fine-tuned GujaratiBERT models combined via majority voting, evaluated against a single GujaratiBERT baseline and six heterogeneous alternatives, including combinations with MuRIL-base, MuRIL-large, IndicBERT, mBERT, BiLSTM, CRF, and a stacked BiLSTM-CRF-GujaratiBERT architecture. All eight models were trained under a consistent budget and evaluated using entity-level F1 on the Naamapadam Gujarati test split. HomoEnsNER achieved the highest F1 (0.8442), surpassing the baseline (0.8347) and every heterogeneous alternative (lowest: 0.7855), indicating that language alignment is a more effective, budget-conscious ensembling strategy than architectural complexity for low-resource Indian language NER. --- ### A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces Authors: Rishabh Shukla, Adithya Santhosh, Shaili Gandhi, Samrudh Moode, Satyandra K. Gupta Published: 2026-08-04 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.03103v1 Diffusion policies have shown strong performance in learning complex, multi-modal behaviors for robotic manipulation. However, their application to contact-rich disassembly tasks remains limited by a key trade-off: the iterative denoising process introduces inference latencies that makes high frequency control difficult, which is essential for realizing dynamic interactions such as chiseling and prying. Recent action-chunking techniques mitigate latency but use an open-loop execution window, rendering the system blind to rapid force transients caused by fracture events. To bridge this gap, we introduce the Diffusion Policy Augmented by Fast Trajectory Generation (DPA-FTG). Compared to recent visual-tactile approaches that focus on positional correction, DPA-FTG decouples low-frequency planning from high-frequency force regulation. At the high level ($5$ Hz), a conditional diffusion model predicts a sequence of latent parameters for selecting a strategy from a learned vocabulary of task primitives. At the low level ($60$ Hz), a lightweight, force-conditioned policy acts as a neural impedance controller, modulating execution in real-time to maintain contact stability. We validate our approach on a bimanual battery disassembly task involving the separation of a compliant sheet. Experimental evaluation demonstrates that DPA-FTG outperforms state-of-the-art baselines, including Reactive Diffusion Policy (RDP). --- ### Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining Authors: Bangjie Sun, Nayoung Kim, Mun Choon Chan, Jun Han Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03101v1 Near-duplicate image matching is crucial for trust and safety, provenance verification, copyright enforcement, and large-scale visual search. Modern platforms increasingly rely on deep perceptual hashes, which map visually similar images to nearby representations despite common image transformations. However, adversarial perturbations can cause near-duplicates to evade matching. We present DualShield, a plug-in defense that improves the robustness of existing deep perceptual hashes without retraining or modifying their underlying models. DualShield combines matching-time randomized smoothing, which aggregates decisions over perturbed reference-query pairs, with publication-time hardening, which adds an optimized imperceptible perturbation to each reference image before publication. Together, these mechanisms provide certified and empirical robustness. DualShield achieves a certified $\ell_2$ radius of approximately 0.3, guaranteeing that query perturbations within this radius cannot evade matching. We further evaluate it against adaptive white-box, black-box, and image-transformation attacks. Across eight deep perceptual hashes and three datasets, DualShield substantially reduces attack success rates while preserving low collision rates. These results show that deep perceptual hashes can be strengthened without costly retraining by improving the matching procedure and hardening reference images before publication. --- ### Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition Authors: Ping Li, Chenhao Ping, Jie Song, Mingli Song Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.03100v1 Knowledge Distillation (KD) offers a promising yet underexplored path for compressing large action recognition models. However, existing KD methods suffer from two key limitations: 1) reliance on fixed input samples leads to suboptimal feature alignment between the frozen teacher (larger model) and the learnable student (smaller model), and 2) applying a uniform distillation strength for all channels fails to account for their varying importance in capturing distinct knowledge (e.g., motion tempo or magnitude) across training epochs. This motivates us to develop an Adaptive Sample-aware Channel-wise Dynamic (ASCD) KD approach, which operates in two stages. First, we use an adaptive sample generation module to create updated samples by incorporating semantics from sample gradients, which are derived by minimizing a feature loss weighted by channel centroid frequency differences at each layer. Meanwhile, crucial motion-related details are preserved by applying a Gaussian mask to frequency features. Second, we employ a channel-wise dynamic distillation module to train student on these generated samples, guided by sample gradients and feature frequencies. For efficiency, samples are updated periodically rather than per epoch. Extensive experiments on three video benchmarks (UCF101, Kinetics-400, Something-Something-v2) and two image datasets (CIFAR-100, ImageNet) demonstrate the state-of-the-art performance of our method. Code is available at https://github.com/mlvccn/ASCD_KD_Action. --- ### What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents Authors: Yifan Guo, Chenghao Li, Zhu Wang, Wei Xu, Yu Li, Yulong Zhu, Zhuo Sun, Bin Guo, Zhiwen Yu Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.03099v1 Foundation models place language throughout embodied agents, but its presence does not show what it contributes or how well that contribution is grounded. This survey separates these two questions. We define five non-exclusive functional roles for language: Specification, Embodied Representation, Action Orchestration, Grounding Regulation, and Execution Coupling. For each role, we trace the path from linguistic content to its embodied consumer and identify the observations or interventions that can test the claimed responsibility. Applying this framework to the reviewed literature reveals a recurring gap between functional use and evidential support. Interpretable or revised linguistic intermediates may be incorrect, go unused, or fail to affect later behavior. Even when actions are directly conditioned on language, system-level success does not by itself isolate language's contribution. We therefore evaluate grounding claim by claim, asking whether the reported evidence supports the specific responsibility assigned to language. Using role claims rather than architectures as the unit of comparison allows us to compare modular and end-to-end embodied agents without extending conclusions beyond the reported evidence. --- ### FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection Authors: Pei Li, Sihan Chen, Delong Ran, Tianshuo Cong Published: 2026-08-04 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.03096v1 Recent advances in video generation models have significantly intensified the deepfake threat, yet the current deepfake video detection benchmarks remain underdeveloped. In particular, the effectiveness of image-level detectors in the video domain has not been systematically assessed. To fill this gap, we present FakeI2V-Bench, a benchmark for evaluating state-of-the-art video-level deepfake detectors in challenging scenarios, with a particular focus on systematically assessing the performance of image-level deepfake detectors in the video domain. FakeI2V-Bench comprises 97,548 videos, containing content generated by the latest powerful generation models and covering a broader range of categories. Using this dataset, we conduct a systematic evaluation of eight video-level detectors and twelve representative image-level detectors. Experimental results show that the best-performing image-level detector achieves an 80.16% AUC, slightly outperforming the strongest video-level detector (i.e., 79.99% AUC). Going beyond benchmarking, we present IV-Bridge, a general framework that enhances the applicability of image-level deepfake detectors to videos. IV-Bridge employs a random forest model with statistical features to aggregate frame-level predictions, allowing eleven image-level detectors to surpass state-of-the-art video-level approaches, with the best-performing variant achieving a 93.80% AUC. Overall, FakeI2V-Bench establishes a rigorous benchmark for deepfake video detection and introduces a novel pathway for extending image-level detectors to the video domain, offering new insights and directions for future research. Code and data are available at https://github.com/CryptoAILab/FakeI2V-Bench. --- ### VIVID: A Culturally Grounded Benchmark Exposing the Figurative Language Gap in Vietnamese NLP Authors: Tu Tran Do, Nhat Ngoc Nguyen, Khanh-Tung Tran, Hoang D. Nguyen, Tu Minh Phuong, Long Hoang Dang Published: 2026-08-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.03095v1 We present VIVID (Vietnamese Idioms for Validation and Interpretation Depth), the first systematic benchmark for evaluating culturally grounded figurative language understanding in Vietnamese. VIVID comprises 1,636 idioms and proverbs annotated with five complexity traits (literal expressions, pragmatic nuances, Sino-Vietnamese terms, uncommon vocabulary, folk knowledge) and seven semantic themes. We establish an evaluation framework combining generative and discriminative tasks, proposing an LLM-as-a-Judge approach with aspect-based prompting validated against human judgment (Cohen's kappa = 0.792). Evaluating eight state-of-the-art models reveals critical gaps: Vietnamese-specialized models drastically underperform multilingual systems (VinaLLaMA-7B: 0.13 vs. GPT-4o: 2.46), and even top models achieve less than 50% of maximum scores. Notably, few-shot prompting does not universally improve performance, with GPT-4o exhibiting degradation due to stylistic overfitting. Our analysis exposes systematic failures including literal over-interpretation, lexical gaps, and pragmatic flattening, demonstrating that current models lack cultural competence for nuanced figurative interpretation. VIVID provides an essential tool for advancing figurative language understanding in culturally rich contexts. --- ### SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation Authors: Wen Wang, Jiahua Bao, Tu Yongsiqi, Yihao Liu, Haotian Zhou, Haoxuan Ma, Mengyu Zhou, Wenkui Fan, Junwei He, Xiaoxi Jiang, Guanjun Jiang Published: 2026-08-04 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.03092v2 We aim to improve model performance in multi-reward reinforcement learning training process. Existing Group reward-Decoupled Normalization Policy Optimization (GDPO) has mitigated the issue of reward signals masking one another during direct scalarization by normalizing each reward dimension separately before aggregation. However, our experiments show that GDPO still struggles to balance reward signals with different granularities. Specifically, in some particular training tasks, the model may receive a dense reward that assigns fine-grained scores ranging from 0.1 to 1.0, together with a sparse reward that provides only binary feedback of either 0 or 1. In such cases, we find that the sparse reward may provide an insufficient optimization signal, preventing its corresponding capability from being effectively reinforced. Therefore, how can we strengthen the optimization signal from the sparse reward without sacrificing the capability already learned from the fine-grained reward? To overcome this limitation, we propose Specialize-and-Merge Online Policy Distillation (SMOPD), a two-stage training method for multi-reward optimization. Stage1-Specialize: SMOPD first employs reward-priority configurations to train multiple reward-specialized teachers, allowing each reward to be learned under conditions where its signal can effectively drive optimization. Stage2-Merge: SMOPD then utilizes online policy distillation to combine the reward-specialized capabilities of these teachers into a single student policy, while maintaining balanced task-level optimization. To validate our method, we conduct experiments on two multi-reward settings: complementary rewards(tool-calling accuracy and format) and conflicting rewards (helpful and harmless rewards). Based on above settings, SMOPD outperforms GDPO across 1.5B, 3B and 7B backbones. ---