Artificial Intelligence
Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
Yanchao Li, Wanhao Liu, Jiaqing Xie et al. (+4 more)
Benchmark gains are often treated as evidence of greater LLM capability. Yet the same gain can reflect different changes in model behavior. A model may reach new answers, or produce answers that were already within reach. Aggregate scores do not distinguish these changes question by question. We establish a question-level audit under fixed budgets, temperatures, and answer formats. A question is realized when the default deployment procedure produces the correct answer. A question is reachable when a specified probe finds that answer within a fixed budget. We first test whether inference-time layer routing can expand reachability. Under a matched budget, random routes match or exceed structured search in all 43 model and task settings. Answer-blind procedures retain almost none of this gain, which instead requires access to the correct answer. We then ask why reachable answers sometimes fail to appear. Across six cases spanning 0.5B to 31B, silencing one identified MLP block repairs 68 to 92 percent of a predefined failure set. We next test whether training closes the gap by expanding reachability. In five of six matched evaluations, deployed performance rises while the reachable ceiling remains flat or falls. For DAPO, the deployed score rises by 14.7 points while the reachable ceiling falls by 13.3 points. Across the settings we audit, realization and reachability therefore do not always change together. Claims of capability expansion should report both realized performance and reachability under matched evaluation conditions. Code is available at https://github.com/LiZaiyuan0619/reachability-not-realization
Read the full abstract ▾
All authors Yanchao Li, Wanhao Liu, Jiaqing Xie, Ben Gao, Yanbo Wang, Tianfan Fu, Yuqiang Li
Artificial Intelligence · Cross-listed from cs.CV
Self-Supervised Representation-Guided Generative Dataset Distillation
Mingzhuo Li, Guang Li, Linfeng Ye et al. (+4 more)
Dataset distillation compresses a large training set into a compact synthetic set while retaining its downstream utility. Most existing methods target randomly initialized networks, whereas modern
vision systems often adapt frozen pretrained encoders with lightweight modules. Distilled samples should therefore preserve the discriminative geometry of the pretrained representation space, which existing generative objectives do not explicitly consider. We propose self-supervised representation-guided generative
dataset distillation (SRG), a framework that translates the SSL geometry into
diffusion guidance. Specifically, SRG constructs class-wise prototypes from real-image SSL representations and performs guidance through three SSL-space objectives for prototype
alignment, inter-class discrimination, and intra-class assignment. During
diffusion sampling, it adopts a stage-wise guidance strategy: early denoising is anchored to the latent of the real image whose SSL representation is nearest to the assigned prototype, whereas later denoising is guided by the SSL-space objectives. This division preserves the visual realism provided by the generative prior while progressively steering samples toward representative and class-discriminative regions of the SSL representation space. SRG consistently outperforms the evaluated generative baselines across multiple
datasets and IPC settings. A cross-encoder evaluation further indicates transfer across pretrained representation spaces. These results demonstrate the effectiveness of representation-guided generation for
dataset distillation with pretrained SSL models.
Read the full abstract ▾
All authors Mingzhuo Li, Guang Li, Linfeng Ye, Jiafeng Mao, Takahiro Ogawa, Konstantinos N. Plataniotis, Miki Haseyama
Artificial Intelligence · Cross-listed from eess.AS
GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model
Guanrou Yang, Tian Tan, Qian Chen et al. (+8 more)
Reinforcement learning for flow-matching text-to-
speech is complicated by deterministic ODE sampling: trajectory-level policy-gradient methods typically convert the ODE into an SDE and track per-step likelihood ratios, introducing
stochastic perturbations and substantial overhead. We propose GROW, a group-relative advantage-weighted on-policy RL method that acts directly on the standard flow-matching objective. For each
prompt, GROW samples a group of on-policy utterances, separately standardizes intelligibility and speaker-similarity rewards within the group, and combines them to reweight flow-matching regression. A Wasserstein-2 velocity penalty anchors the updated model to a frozen pretrained reference. A group-mean reward baseline is introduced to convert reward weighting into advantage weighting. For strong pretrained TTS models with concentrated rewards, positive exponential weighting is dominated by reward-agnostic self-imitation, whereas a zero-mean signed advantage preserves effective within-group credit assignment. Instantiated on DiTAR and evaluated on LibriSpeech and Seed-TTS EN/ZH, GROW reduces average WER from 2.016 to 1.558 and raises speaker similarity from 0.676 to 0.715 while keeping UTMOS. With 10-NFE training rollouts and 32-NFE evaluation, GROW retains comparable performance while training 2.9x faster than 32-NFE DiTAR-GRPO. We will open-source complete GROW codes, faithful DiTAR reproduction, and all model checkpoints.
Read the full abstract ▾
All authors Guanrou Yang, Tian Tan, Qian Chen, Ziyang Ma, Yakun Song, Zhikang Niu, Qi Chen, Wenming Tu, Haitao Li, Shan Yang, Xie Chen
Artificial Intelligence
The Agent Operating System (AOS): A Reference Operating Architecture for Distributed Agentic Systems
Ankur Sharma and Deep Shah
Large
language models have transformed artificial intelligence from isolated prediction services into components of long-running, distributed systems that reason, invoke tools, retrieve external state, delegate tasks, and act on behalf of users and organizations. The surrounding ecosystem has responded with
agent frameworks, workflow engines, model-serving platforms,
memory systems, communication protocols, and observability tools. These technologies improve execution, but they do not provide a stable, implementation-independent operating architecture for governing intent, selecting capabilities, preserving authority across delegation, controlling uncertainty, coordinating runtime behavior, and reconstructing why consequential actions occurred. This paper proposes the
Agent Operating System (AOS), a vendor-neutral reference operating architecture for distributed agentic systems. AOS contains two internal planes: a Control & Governance Plane responsible for intent, policy, trust, authority, confidence, auditability, observability, and human oversight; and a Runtime & Coordination Plane responsible for
agent lifecycle, workflow coordination, model and tool routing, context and
memory coordination, scheduling, traffic management, and runtime assurance. Platform services, Linux or Windows, container runtimes, and physical infrastructure remain outside the AOS boundary and are integrated through explicit interfaces. The paper specifies AOS concepts, invariants, interface objects, optimization objectives, deployment profiles, and reliability responsibilities. It also identifies tradeoffs and unresolved research questions. AOS is not presented as a replacement for existing frameworks or infrastructure; it is proposed as the operating architecture through which heterogeneous components can be composed into governable, reliable, observable, and interoperable agentic systems.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated Learners
Unggi Lee, Sookbun Lee, Yeil Jeong et al. (+3 more)
Large
language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into
agents operating over a learning management system (LMS). Yet tutoring is long-horizon, since a learner improves over days and weeks rather than in a single turn, and no
benchmark evaluates an
agent tutor across a sustained relationship. We introduce EduClaw-Bench, a
benchmark that places an
agent tutor in a continuous 30-day relationship with a simulated learner grounded in knowledge tracing (KT), whose knowledge-concept mastery, from a KT model trained on real-student data, drives its answers and is probed for learning gain across 55 scenarios. Each
agent is scored on three primary axes (learning gain, responsiveness, and helpfulness) and two curriculum-design axes (Gagné and Rosenshine), with helpfulness and the curriculum axes judged by a cross-family panel of three LLM judges. Evaluating 10
agent adapters over three base-model tiers yields two findings that single-tier, single-session evaluation cannot reach. First, tutoring quality belongs to the base model and the
agent harness together rather than either alone. Second, almost no combination sustains good tutoring over the full horizon. A calibration check ($\text{ECE}=0.049$) and a live-classroom field study confirm that the simulated learner and its measurements track reality. Our work is a step toward trustworthy AI tutors for future education.
Read the full abstract ▾
All authors Unggi Lee, Sookbun Lee, Yeil Jeong, Eunjoo Lee, Minchul Shin, Hoilym Kwon
Artificial Intelligence · Cross-listed from cs.CL
Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling Approach
Tianbao Jiang, Weicong Ni, Gerard de Melo et al. (+1 more)
Post-training reinforcement learning (RL)
algorithms are commonly used to align large
vision-
language models (LVLMs) with human intent and the requirements of visual
reasoning tasks. However, existing RL-based
alignment methods are often resource-intensive and encounter mismatches between training objectives and inference-time distributions. To bridge this gap, we propose a novel test-time
alignment approach that leverages trajectory-guided structured sampling for dynamic inference-time refinement, achieving better
alignment with visual grounding and ensuring logical consistency. Our approach begins with curating a
reasoning memory bank via a trajectory learning
algorithm, which decomposes complex question solving into ordered sequences of predefined
reasoning patterns. It subsequently accomplishes inference-time
alignment by first collecting trajectories from
reasoning memory bank to establish a global structural
reasoning prior, and then using an iterative Markov Chain Monte Carlo (MCMC)
algorithm for localized multi-objective refinement of the
reasoning trace. Experiments across multiple
multimodal reasoning datasets demonstrate that our approach significantly improves accuracy without incurring prohibitive inference overhead. These results establish trajectory-guided test-time sampling as a scalable and effective alternative to traditional post-training
alignment, particularly for complex visual
reasoning tasks.
Read the full abstract ▾
All authors Tianbao Jiang, Weicong Ni, Gerard de Melo, Linlin Wang
Artificial Intelligence
When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models
Yu Feng, Chunting Zang, Chen Shen et al. (+4 more)
Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled
prompt-response pairs. We audit two widely used safety-guard training
datasets, WildGuardMix and GR-Train, and find that among responses to harmful
prompts, refusal expressions co-occur almost exclusively with unharmful labels. This imbalance motivates what we term the refusal-cue shortcut: inserting a refusal cue into a harmful response could flip the guard's verdict from harmful to unharmful. The shortcut affects not only guards trained on these
datasets but also officially released models such as LlamaGuard3 and Qwen3Guard whose training data is undisclosed. It persists across response positions and is generally stronger in smaller variants within a family. To mitigate it, we adapt sparse complementary masking as a lightweight post-hoc intervention that identifies and suppresses a small set of shortcut-associated
attention heads and MLP
neurons without retraining. On two primary
benchmarks, the intervention achieves an approximately 79% relative reduction in response-initial detection failures induced by refusal cues, while preserving standard detection performance. Although optimized using cues at a single response position, the suppression effect transfers to unseen positions and
datasets, suggesting that shortcut manifestations across positions are partly mediated by shared internal components. Further analysis provides evidence that shortcut reliance and legitimate refusal recognition are partially functionally separable, as suppressing the shortcut broadly preserves the guard's ability to recognize genuine refusals.
Read the full abstract ▾
All authors Yu Feng, Chunting Zang, Chen Shen, Rui Miao, Ge Teng, Weidong Cai, Jieping Ye
Artificial Intelligence
TumorBoard: Evidence-Grounded Multi-Agent Decision Support for Longitudinal Neuro-Oncology
Yantong Liu, Zheyu Zhang, Runpeng Liu et al. (+3 more)
Neuro-oncology decisions require coordinated interpretation of serial MRI, pathology, molecular markers, treatment history, performance status, and evolving guidelines. We present TumorBoard, a multi-
agent decision-support system built around a shared longitudinal case state and an auditable claim-evidence ledger. Specialist
agents for radiology, neuropathology, molecular diagnosis, guidelines, and therapy planning produce atomic claims with provenance. An
adversarial critic exposes contradictions, and a safety governor releases, qualifies, or defers recommendations according to evidence sufficiency and temporal validity. On a 360-case hidden
benchmark at a matched
token budget, TumorBoard achieved an action F1 of 0.772 and evidence entailment of 0.914. It exceeded the strongest typed-council baseline by 3.1 percentage points (95% CI: 1.6 to 4.7, adjusted p = 0.0012), while recommendation-to-evidence coverage reached 0.927. Under evidence deletion, the system deferred 84.2% of unsafe cases and limited harmful recommendations to 5.8%. The safety governor reduced harmful release by 7.8 percentage points at a false-deferral cost of 4.3 percentage points. Ablation studies of the ledger, critic, and governor produced the predicted failure patterns, establishing structured coordination as the source of the measured multi-
agent advantage.
Read the full abstract ▾
All authors Yantong Liu, Zheyu Zhang, Runpeng Liu, Mu Xitang, Seong-Yoon Shin, Hyun-Ae Lee
Artificial Intelligence
Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA
Jiwon Lee, Yong-chan Park, Jungin Hong et al. (+1 more)
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.
Read the full abstract ▾
All authors Jiwon Lee, Yong-chan Park, Jungin Hong, U Kang
Artificial Intelligence · Cross-listed from cs.CR
Attribute-based Undetectable Watermarking for Generative AI Models
Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel et al. (+1 more)
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 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 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.
Read the full abstract ▾
All authors Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel, Er-Cheng Tang
Artificial Intelligence
Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
Qiming Bao, Sherry J. H. Feng, Kim Chester Eugenio et al. (+1 more)
Structure-preserving de-identification replaces each detected identifier with a realistic same-type surrogate ("Anna S." -> "Maria S.") rather than a tag such as [NAME]. If downstream PHI detectors no longer recognise surrogates, hiding-in-plain-sight protection and second-pass safety nets weaken. We ask: on the spans a de-identifier actually replaced, do detectors find the surrogate as often as the original value? We call this detectability preservation and treat it as a proxy, not a full measure of utility. Our paired protocol (i) scores detectability only on replaced spans, separately from coverage; (ii) runs an identical heterogeneous detector panel on original and transformed text; and (iii) bounds the paired change with document-level cluster-bootstrap equivalence testing and posterior probabilities instead of significance tests. For one commercial transform on 7 clinical and general-PII
benchmarks in 7
languages (1,750 documents, 5,333 replaced spans, 11 detectors), masked-span recall moves from 75.8% to 74.6% (90% CI of the change [-1.62, -0.82] points; posterior probability > 0.99 of lying within +/-2 points). The change reaches 2-3 points on dense Spanish and Dutch text, and replaced spans are easier to detect than unreplaced ones (+16.6 points), so the result describes the replaced population only. Coverage is a separate, weaker axis (48% of gold PHI on MEDDOCAN). On financial, legal and enterprise text (750 documents, 10 detectors) the pooled result replicates (72.4% -> 72.8%), but rule-based and fine-tuned detectors lose 2-4 points on finance, and the transform edits substantial non-PII text. Redaction and Faker baselines give reference points. We release per-span predictions and analysis code.
Read the full abstract ▾
All authors Qiming Bao, Sherry J. H. Feng, Kim Chester Eugenio, Meng Fon
Artificial Intelligence · Cross-listed from cs.GT
EFX Allocation In (Multi)Hypergraphs
Thanasis Lianeas, Alkmini Sgouritsa and Minas Marios Sotiriou
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.
Read the full abstract ▾
Artificial Intelligence
Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi et al. (+1 more)
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' $\kappa = 0.71$). 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.
Read the full abstract ▾
All authors Saqib Shouqi, Abdullah Nazly, Januki Wanniarachchi, Ravisha De Alwis
Artificial Intelligence
Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational Reasoning
Sahil Al Farib, Momota Ahsana Meem, Sheikh Redwanul Islam et al. (+1 more)
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.
Read the full abstract ▾
All authors Sahil Al Farib, Momota Ahsana Meem, Sheikh Redwanul Islam, Md. Tanvir Raihan
Artificial Intelligence
UniGD: A Unified Generative-Discriminative Framework for Industrial Retrieval
Shujie Ji, Yawei Kong, Yilin Zhao et al. (+3 more)
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.
Read the full abstract ▾
All authors Shujie Ji, Yawei Kong, Yilin Zhao, Li Wang, Xialong Liu, Peng Jiang
Artificial Intelligence · Cross-listed from cs.LG
Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation
Sicong Chang, Yidan Shen, Wen Yu et al. (+3 more)
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.
Read the full abstract ▾
All authors Sicong Chang, Yidan Shen, Wen Yu, Jiefu Chen, Xin Fu, Renjie Hu
Artificial Intelligence
AI-guided deep visual proteomics reveals recurrence-associated morpho-molecular signatures within triple-negative breast cancers
Yesung Cho, Ji Hwan Park, Chan Il Kim et al. (+28 more)
Outcome informed AI can localize prognostically relevant regions in digital pathology, but directly characterizing the molecular basis of these spatial predictions remains challenging. Here, we developed an outcome informed, AI-guided deep visual proteomics framework that uses recurrence-risk heatmaps to guide physical tissue sampling and mass spectrometry-based spatial proteomics in triple-negative breast cancer (TNBC). In 156 patients, high- and low-risk regions coexisted within the tumor compartment and showed distinct
nuclear and architectural features, indicating intratumoral variation beyond broad tissue identity. Guided by these maps, we physically isolated and profiled 46 AI-defined high- and low-risk tumor regions from two recurrent cases. High-risk regions were enriched for mitotic programs, whereas low-risk regions showed immune- and antigen-presentation-associated programs. We used
proteins that consistently differed between high- and low-risk regions to construct a 13-
protein composite. The composite showed a significant effect to discriminate highly recurrent patients from less recurrent patients in an expanded TNBC cohort, while the corresponding transcript-based score showed a similar trend in METABRIC. Integrating the
protein composite with the H&E-derived risk score improved out-of-bag discrimination, increasing the C-index from 0.679 to 0.739 and the 5-year time-dependent AUC from 0.675 to 0.770. These findings establish outcome-informed H&E risk maps as spatial guides for molecular discovery, extending prognostic AI from prediction toward direct biological interrogation of recurrence-associated tissue states.
Read the full abstract ▾
All authors Yesung Cho, Ji Hwan Park, Chan Il Kim, Hyewon Kim, Honglan Li, Yumin Lee, Geongyu Lee, Sujeong Hong, Seong Min Park, Yoonyoung Lee, Hee Sool Rho, Sumin Lee, Amos Chungwon Lee, Changhwan Lee, Hwanyoung Shim, Hyunwook Kim, Hyeji Shin, Sanha Park, Jihoon Yu, Yoon Hee Shin, Sooheon Kim, Hyunjin Park, Seung Min Park, Sangwan Kim, Yujung Kim, Jinwon Jeong, Sung-Im Do, Eun-Young Kim, Dongmyung Shin, Ingu Do, Jongbae Park
Artificial Intelligence · Cross-listed from stat.ML
Minimax-Optimal Semiparametric Contextual Dynamic Pricing with Multimodal Revenue
Xueping Gong, Zhuoluo Zhang, Zhaowei Miao et al. (+1 more)
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.
Read the full abstract ▾
All authors Xueping Gong, Zhuoluo Zhang, Zhaowei Miao, Jiheng Zhang
Artificial Intelligence · Cross-listed from cs.CL
Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning
Meicong Zhang, Tiancheng Su, Jiahao Cheng et al. (+3 more)
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.
Read the full abstract ▾
All authors Meicong Zhang, Tiancheng Su, Jiahao Cheng, Guoxiu He, Xinqi Tao, Dejia Song
Artificial Intelligence
Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents
Xiaolong Sun, Qichao Wang, Hangyu Li et al. (+1 more)
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.
Read the full abstract ▾
All authors Xiaolong Sun, Qichao Wang, Hangyu Li, Liang Chen
Artificial Intelligence · Cross-listed from cs.CV
Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory Unfolds
Ning Zhu, An Chen, Mengfei Zhao et al. (+4 more)
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
Read the full abstract ▾
All authors Ning Zhu, An Chen, Mengfei Zhao, Juntao Xu, Jingze Liang, Boyuan Gu, Liang-Jian Deng
Artificial Intelligence
Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search
Qinglong Hu, Qingfu Zhang, Fei Liu et al. (+3 more)
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.
Read the full abstract ▾
All authors Qinglong Hu, Qingfu Zhang, Fei Liu, Xialiang Tong, Kun Mao, Mingxuan Yuan
Artificial Intelligence · Cross-listed from cs.RO
DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units
Haoyu Gu, Haotian Lu, Jingrun Du et al. (+1 more)
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.
Read the full abstract ▾
All authors Haoyu Gu, Haotian Lu, Jingrun Du, Xiao-Ping Zhang
Artificial Intelligence · Cross-listed from cs.LG
Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning
Zezheng Wu, Xinghe Cheng, Qinggang Zhang et al. (+4 more)
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.
Read the full abstract ▾
All authors Zezheng Wu, Xinghe Cheng, Qinggang Zhang, Haoran Luo, Jiapu Wang, Qing Yang, Jingwei Zhang
Artificial Intelligence
Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVR
Yongshi Ye, Liang Zhang, Yidong Chen et al. (+2 more)
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.
Read the full abstract ▾
All authors Yongshi Ye, Liang Zhang, Yidong Chen, Xiaodong Shi, Biao Fu
Artificial Intelligence · Cross-listed from econ.TH
Optimal Liability Design for Medical AI
Rui Mao, Tingliang Huang and Houcai Shen
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.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Paribesh Regmi, Qingshuang Chen, Chi Zhang et al. (+3 more)
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 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 an adaptive
token pruning strategy specifically designed for
video processing. Crucially, the
pruning ratio is determined adaptively based on the content of each
video. This is achieved by analyzing the correlation structure of
token embeddings to quantify redundancy, enabling dynamic
token allocation that retains more
tokens for dynamic scenes while aggressively
pruning repetitive or static content. 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%.
Read the full abstract ▾
All authors Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda Mao
Artificial Intelligence · Cross-listed from cs.RO
A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces
Rishabh Shukla, Adithya Santhosh, Shaili Gandhi et al. (+2 more)
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).
Read the full abstract ▾
All authors Rishabh Shukla, Adithya Santhosh, Shaili Gandhi, Samrudh Moode, Satyandra K. Gupta
Artificial Intelligence · Cross-listed from cs.CR
FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection
Pei Li, Sihan Chen, Delong Ran et al. (+1 more)
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.
Read the full abstract ▾
All authors Pei Li, Sihan Chen, Delong Ran, Tianshuo Cong
Artificial Intelligence · Cross-listed from cs.LG
SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation
Wen Wang, Jiahua Bao, Tu Yongsiqi et al. (+8 more)
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.
Read the full abstract ▾
All authors Wen Wang, Jiahua Bao, Tu Yongsiqi, Yihao Liu, Haotian Zhou, Haoxuan Ma, Mengyu Zhou, Wenkui Fan, Junwei He, Xiaoxi Jiang, Guanjun Jiang