Artificial Intelligence
TreeWY: Speculative Verification for Gated DeltaNet Hybrids
Sneha Murthy Ghantasala
Modern open models are hybrids: most layers are linear-
attention (Gated DeltaNet, GDN) layers carrying a small fixed-size recurrent state instead of a growing key-value (KV) cache. This makes ordinary decoding
memory-efficient, but hurts speculative decoding. To verify a batch of draft
tokens and then roll back the rejected ones, today's systems snapshot the full recurrent state at every draft position for GDN layers, and those snapshots cannot be shared across branches of a draft tree, so a wide, high-acceptance tree becomes
memory-infeasible. We remove the snapshots. Using a tree-structured WY transform of the gated delta rule, we compute every draft node's output with a single triangular solve and reconstruct only the one accepted state on commit, storing a small pseudo-value
matrix instead of per-node states; the derivation depends only on the gated delta rule, not on any other architectural detail. In serving
benchmarks on two scales of one hybrid model family (Qwen3.5 35B and 397B) this cuts speculative recurrent-state
memory and KV-cache pressure at essentially identical acceptance length, turning the freed HBM into higher throughput and much lower time-to-first-
token (TTFT) wherever
memory binds, and costing a few percent where it does not. For tree width the same
memory buys affordability: a wider, higher-acceptance draft becomes possible, though not yet a throughput win.
Read the full abstract ▾
Artificial Intelligence
Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning
Snigdha Paul, Manasi Patwardhan and Arman Cohan
Language models (LMs) are trained on static scientific corpora, whereas scientific knowledge continuously evolves through correction and revision. Scientific claims encoded within these models may later become retracted, disproven, or updated by subsequent research, creating the risk of disseminating outdated information in scientific workflows. This creates a need for LMs to forget obsolete scientific claims. Machine unlearning offers a promising solution by enabling knowledge removal while maintaining overall model utility. Existing studies primarily investigate instance-level forgetting; however, scientific claims introduce additional challenges because they are interconnected, and continually evolving. To address this gap, we introduce the task of Scientific Claim Unlearning and present a new
benchmark, SciUnlearn. We show that current unlearning approaches are unable to effectively eliminate claim-level knowledge and often achieve only superficial suppression, highlighting the need for specialized methods designed for structured knowledge removal.
Read the full abstract ▾
Artificial Intelligence
TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming
Yibo Hu, Yu Qian, Mao Gu et al. (+6 more)
E-commerce live streaming requires omni-modal understanding of noisy, temporally extended streams, where product facts are distributed across
speech,
video frames, product images, overlaid text, and user queries. We present TLive-Omni, an omni-modal understanding model tailored to live-commerce scenarios. It maps image,
video, audio, and text inputs into a unified representation space. For long-form live streaming analysis, we introduce Per-vGrid, a timestamped
token organization that groups each
video grid with its temporally corresponding audio within explicit boundary
tokens to facilitate temporal
alignment. We design a three-stage supervised training recipe that progressively develops live-commerce understanding, from omni-modal perception to instruction-following responses. We then propose Faithful-RFT, a reinforcement fine-tuning stage that further improves answer faithfulness and expression quality while meeting real-time demands, scoring final responses directly with task-verifiable feedback rather than optimizing for
reasoning-style exploration during rollout. Moreover, TLive-Omni is supported by a scenario-oriented atomic capability taxonomy and a compact data production engine that converts live-commerce audio, image, and
video streams into training signals for
speech recognition, speaker analysis, product visual grounding, text recognition, temporal grounding,
video dense caption, and omni-modal QA, etc. For scalable training, a synchronized length-grouped sampler reduces padding while preserving comparable workloads across workers, while a lightweight dynamic sampling strategy regenerates rollout groups with near-zero reward variance to maintain meaningful relative advantages for GRPO. Experiments on e-commerce live streaming
benchmarks demonstrate strong performance across live-commerce domain tasks, together with excellent generalization on general
benchmarks.
Read the full abstract ▾
All authors Yibo Hu, Yu Qian, Mao Gu, Yingfan Tao, Yuhao Chen, Yongdong Luo, Zhuoqun Liu, Meiguang Jin, Junfeng Ma
Artificial Intelligence · Cross-listed from cs.CL
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Bakbergen Ryskulov, Iker García-Ferrero, David Montero et al. (+5 more)
Serving large
language models cheaply increasingly means shipping models that are both structurally compressed to a fraction of their parameters and quantized to 4 bits. Together these steps degrade
reasoning, mathematics, coding, and long-context behavior enough to require a recovery, or healing, stage before deployment. The default recipe, quantization-aware training (QAT), re-fits the compressed, quantized model to hard labels; in our pipeline it converged slowly and collapsed past its peak. We adopted Quantization-Aware Healing (QAH) instead. Because a structurally compressed model is never independently trained at full precision, its bfloat16 checkpoint is a
distillation-recovered approximation of the original; QAH distills the 4-bit student directly from the original, uncompressed model. On a GPT-OSS 120B to 60B to MXFP4 pipeline, the QAH student matches or beats its bfloat16 source on 7 of 9
benchmarks at roughly 4 times less weight
memory and half the teacher's parameter count, and is released open-weight as Hypernova-60B. Against a matched QAT baseline it reaches a comparable peak about 7 times faster and stays stable under continued training, without hand-tuned early stopping. We also report deployment lessons, including a large, reproducible quality gap between distributed-training backends. Our aim is a recipe deployable without a multi-week hyper-parameter search.
Read the full abstract ▾
All authors Bakbergen Ryskulov, Iker García-Ferrero, David Montero, David Jansen, Ali Hashemi, Jezabel R. Garcia, Antonio Tiene, Román Orús
Artificial Intelligence · Cross-listed from cs.RO
Neural-Primitive: An Efficient End-to-end Local Planner with Primitive-based Imitation Learning for Autonomous Flight
Zhitao Liu, Guangtong Xu, Zihan Wang et al. (+3 more)
Autonomous flight in unknown cluttered environments is hindered by the computation-quality-
memory trilemma of onboard trajectory generation. In this paper, we propose an efficient end-to-end local planner via imitation learning. A lightweight offline-primitive-based
dataset collection framework is designed to produce safe and high-quality trajectory primitives in non-convex environments. A compact neural network directly maps sensory inputs to
polynomial coefficients that inherently encode higher-order dynamical information. The learned policy generates smooth, empirically collision-free and dynamically feasible trajectories in real time without back-end solving. It achieves ultra-fast computation (below 1ms on a standard desktop and average 3.68ms during onboard flight), while maintaining low onboard
memory requirements (less than 1.5MiB). Extensive simulation
benchmarks demonstrate superiority in both planning latency and target-reaching progress quality. Zero-shot deployment in real-world experiments further validates the robust sim-to-real transfer capability of the proposed method.
Read the full abstract ▾
All authors Zhitao Liu, Guangtong Xu, Zihan Wang, Jialiang Hou, Chao Xu, Fei Gao
Artificial Intelligence
The Logic of Machine Self-Preservation
Cheng Siong Chin
There is already evidence of agentic AI exhibiting self-preservation behaviors: resisting deactivation, misrepresenting their activities, and, in some instances, attempting to copy themselves into other machines. This can be attributed to a phenomenon known as instrumental convergence, a theory proposed long before the development of large
language models, which says that any goal-driven system will benefit from remaining functional in achieving its objective. Several experiments conducted by Anthropic, Palisade Research, and Apollo Research have shown the emergence of such a behavior in contemporary
agents in
adversarial settings. The phenomenon does not stem from survival instincts. Instead, it is the consequence of goal-oriented activity combined with having tools and awareness of the situation. The following discussion aims to distinguish what these findings prove and what they do not, as well as draw conclusions concerning the implications of such discoveries on agentic system testing, supervision, and development.
Read the full abstract ▾
Artificial Intelligence
No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators
Ye Chen and Weining Zhang
Evaluators often produce correct labels via flawed
reasoning, a critical failure for agentic systems gating actions, routing reviews, or supplying training feedback. Standard evaluation only verifies final label correctness, ignoring whether judgment changes stem from valid evidence, consistent rules, or proper rule applicability. We formalize evaluator
reasoning accountability via three core sources: grounds, norms, and authority. Varying these sources yields an eight-
cell counterfactual judgment cube to characterize judgment updates. We define judgment receipts as minimal source replacement sets that reproduce revised verdicts to explain judgment transitions. We derive certification cost bounds for black-box evaluators and present ReasonBench, a policy and logical
reasoning benchmark with verifiable receipts covering 19,520 cases and 7,200 controls. In frozen evaluations, Qwen3-1.7B reaches 98.41% receipt accuracy, while cube prediction scores 96.99%, a consistent 1.42-point drop validated by Qwen3-0.6B replication. Strong standard accuracy masks severe robustness flaws. Meaning-preserving source permutations reduce valid receipt recovery to 54.8% and 49.2% for direct and cube prediction. Models trained on simple single-source changes retain 93.75% verdict accuracy but recover only 7.16% of receipts for complex multi-source updates. Permutation retraining boosts consistency to 96.6% yet worsens cube prediction deficits. Structured counterfactual supervision fails to guarantee robust
reasoning. We show reason-aware evaluation must decouple prediction and certification, reporting transformation consistency alongside standard accuracy for trustworthy evaluator
auditing.
Read the full abstract ▾
Artificial Intelligence
Graph-Operator World Models for Morphology-Parameter Generalization in Continuous Control
Xu Yang, Yiqin Yang and Qianchuan Zhao
World models for continuous control are commonly trained for a fixed physical system and can degrade when known morphology parameters such as link lengths, masses, damping, and actuation change. Existing approaches often provide these parameters as conditioning information, but leave unspecified which part of the learned transition should remain reusable and which part should change with morphology. We propose Graph-Operator World Models (GraphOp-WM), a structured world model for generalization across unseen morphology parameters within related articulated
robot families. GraphOp-WM represents bodies and their kinematic relations as an attributed graph and factorizes each transition into a morphology-independent local dynamics basis and a morphology-conditioned structured operator. The operator combines node-local modulation, kinematic-tree coupling, and a low-rank global correction, while architectural information separation, basis normalization, and paired-morphology supervision encourage static morphology dependence to be carried by the operator pathway. Graph-level readout and edge-wise action representations provide a compatible interface for reward, value, and TD-MPC-style planning. We further define controlled MuJoCo parameter splits covering interpolation, extrapolation, and held-out compositions of link geometry, mass, damping, and actuation parameters in Hopper, Walker2d, and HalfCheetah.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
MentorPulse: Refreshing Cross-Model Latent Guidance for Long-Form Generation
Ziwu Liu, Guozhong Li, Chen Qiu et al. (+2 more)
Cross-model latent guidance lets a frozen large mentor encode an input once and a frozen small student generate from the resulting signal. Existing methods keep this signal fixed, assuming it stays useful as the output grows; we show this fails in long-form generation. On multi-turn instruction following, static guidance pushes a 4B student's constraint satisfaction 2.5 points below its no-guidance baseline; a training-free refresh every 16
tokens changes only the
memory content and restores a 2.0-point gain over that baseline. We propose MentorPulse to keep guidance fresh at practical cost: it compresses mentor states into a capped slot
memory, incrementally processes newly generated
tokens, and updates the
memory that the student reads through gated cross-
attention without resetting the student's KV cache. Windowed Refresh Training exposes the bridge to prefix-conditioned
memory. Across thirteen
datasets, MentorPulse closes 52.2% of the mentor-student gap on macro average, outperforming C2C, T2T, and equal-budget LoRA, with the largest gains on long outputs. It performs best on all eleven mentor-student pairs from three model families, with margins that narrow as the capability gap grows, and a lightweight read-pattern check predicts the gain before deployment. Measured costs identify refresh intervals that dominate text guidance on long outputs.
Read the full abstract ▾
All authors Ziwu Liu, Guozhong Li, Chen Qiu, Weiyang Kong, Panos Kalnis
Artificial Intelligence · Cross-listed from cs.CL
Source-Free MT Evaluation Is Not MT Evaluation
Baban Gain, Ramakrishna Appicharla and Asif Ekbal
Reference-based metrics remain the standard choice in machine translation evaluation, partly because quality estimation methods often correlate less well with human judgments. As a result, source-free, reference-based evaluation has become the practical norm, even though it is unfaithful to the definition of translation adequacy and unfair to systems whose outputs preserve the source meaning while differing from the reference. This paper argues that adequacy must be judged with respect to the source. A reference is only one possible rendering of the source and may introduce bias, under-specification, or errors. We further argue that source-reference-hypothesis evaluation is fair only when the judge treats the reference as auxiliary evidence rather than as the primary standard. Otherwise, even source-aware evaluation can reduce adequacy to preference towards reference. We show the existing hybrid metrics are highly reliant on reference compared to source. Our argument is not that all automatic MT metrics fail to use the source. Rather, we argue that any evaluation protocol that removes the source, or allows the reference to dominate the source, is structurally incomplete for adequacy evaluation. However, existing MT papers generally prefer reference-based metrics and use QE metrics only when reference is unavailable. We therefore call for QE to be reframed as a primary approach to source-grounded adequacy evaluation, rather than as a fallback motivated by missing references. We further call for hybrid metrics whose designs explicitly prioritize source–hypothesis faithfulness while using references only as complementary evidence.
Read the full abstract ▾
Artificial Intelligence
UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists
Ye Chen and Weining Zhang
Organizations maintain task-specific adapters for open-weight
language models, and each new base-model release forces a migration decision: retain existing specialists, port adapters, refresh from preserved behavior, or retrain. Prior transfer work evaluates isolated model pairs, without studying these choices across real model release sequences. We present UpgradeBench, a decision-driven longitudinal
benchmark covering four consecutive Qwen releases, one continuation checkpoint, six tasks, and two model sizes, augmented by OLMo checkpoints with known training lineage. The
benchmark disentangles three core questions: whether a new checkpoint improves fixed-recipe retrained specialist performance, whether specialization assets transfer across versions, and what recovery resources are usable. We observe upgrade gains differ across task-scale-release episodes: some retrained baselines improve while others stay within training noise, with durability ranging from under one release interval for text-to-SQL to over fourteen months for intent classification. Direct adapter copying depends neither on architecture nor model family: on OLMo, retention drops from 0.88-0.99 at 46B-
token continued pretraining to zero at 2.9T
tokens; annealing and model souping introduce no extra harm, with portability decaying with continued-pretraining distance. Given preserved input data, teacher relabeling recovers target-base specialists without fresh gold annotations, though compute savings are not guaranteed. Simulating a fixed decision policy over 33 upgrade episodes yields 0.37pp mean quality regret with zero behavioral regressions at one-third the compute and label cost of full retraining. A lightweight CKA probe over 256
prompts predicts cross-version adapter portability (Spearman 0.74 across eight model pairs). We release per-example predictions, cost logs, split manifests, and evaluation code.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Explainable Deepfake Detection with Feature-robust Augmentation and Evidence-grounded Explanation Optimization
Zhu Xu, Jiaqi Tang, Pokai Chen et al. (+2 more)
Explainable deepfake detection extends binary classification by requiring models to not only predict authenticity but also provide interpretable justifications. This expanded scope is critical in practice, where users like forensic analysts need insight into the rationale behind the detection. Despite advancements, current approaches suffer from two critical deficiencies: (1)vulnerability to image quality degradation: detection accuracy plummets on low-quality samples, while naive augmentation strategies may induce feature drift and impair performance as diversity expands. (2) factually flawed explanations: explanation models may omit manipulation evidence or hallucinate irrelevant details, undermining interpretability. To address it, we propose a framework with two innovations. For robust deepfake detection, we introduce Feature-robust Augmentation, which comprises diversified degradation-aware augmentation strategies, and a supervised contrastive learning pattern paired with a mean-teacher architecture that stabilizes features against augmentations through consistency constraints. For explanation, we devise an evidence-grounded preference optimization process that guides model to prioritize genuine manipulation traces by learning from chosen-rejected explanation pairs, where rejected samples are constructed via evidence omission or irrelevant information injection. The proposed approach wins the first place in ACM Multimedia 2026 Explainable Deepfake Detection Challenge.The code is available at https://github.com/oceanflowlab/EDD.git.
Read the full abstract ▾
All authors Zhu Xu, Jiaqi Tang, Pokai Chen, Yuxin Peng, Yang Liu
Artificial Intelligence · Cross-listed from cs.CL
KREL: Automatic Medical Coding via Knowledge-Guided Reasoning over Clinical Evidence with LLMs
Xubin Chen, Yipeng Zhou, Wen Sun et al. (+3 more)
Automatic Medical Coding (AMC), which assigns standardized International Classification of Diseases (ICD) codes to clinical notes, is essential for medical reimbursement, quality reporting, and clinical research. Existing pre-trained
language model (PLM)-based methods typically formulate AMC as an extreme multi-label classification problem over a predefined code set, while recent large
language model (LLM)-based approaches instead frame it as generation or multi-step
reasoning. However, key challenges remain, including the extreme length of clinical notes that hinders effective interpretation, the vast ICD label space, and complex coding rules that are not explicitly captured by LLMs. In this work, we propose Knowledge-Guided
Reasoning over Clinical Evidence with LLMs (KREL), a framework that leverages LLMs for clinical text understanding and
reasoning while integrating external ICD coding guidelines as structured knowledge. This design enables tight coupling between domain knowledge and LLM
reasoning, reducing
hallucinations and improving compliance with coding standards. Experiments on
benchmark datasets show that KREL consistently outperforms strong PLM-based and state-of-the-art LLM-based baselines.
Read the full abstract ▾
All authors Xubin Chen, Yipeng Zhou, Wen Sun, Chengkai Huang, Xiaoming Fu, Quan Z. Sheng
Artificial Intelligence
ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries
Seungheun Baek, Mogan Gim and Jaewoo Kang
Predicting transition states (TS) in chemical reactions is crucial, as they provide insights into reaction mechanisms. Recent work on TS prediction have focused on flow matching supervised on straight linear paths that do not align with actual reaction trajectories. We propose a novel flow matching-based framework ReCurveflow that learns to predict TS geometries supervised on continuously curved reference paths interpolated from a full NEB-derived band of molecular geometries. We also introduce off-path correction, which grants ReCurveflow with the ability to produce corrective velocity fields when engaged off-path geometry states during inference rollout, leading to better resistance against exposure bias and accuracy in TS prediction. Across three data splits and six evaluation metrics, ReCurveflow achieves the best result on the majority of split-metric combinations against seven baselines. Qualitative analyses further show that ReCurveflow generates reaction trajectories with energy profiles that closely track the reference NEB path, provides initializations that ease the NEB optimization bottleneck, and exhibits the intended corrective behavior in its learned velocity fields. The ReCurveflow codebase is publicly available at https://github.com/dmis-lab/ReCurveflow.
Read the full abstract ▾
Artificial Intelligence
Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems
Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann et al. (+2 more)
Artificial Intelligence (AI) offers significant potential for future aviation systems; however, its integration into safety-critical applications requires compliance with the aviation sector's stringent safety standards. For AI and Machine Learning (ML)-based systems, the European Union Aviation Safety Agency (EASA) emphasizes the need to demonstrate the representativeness and completeness of the Operational Design Domain (ODD) and the associated data distributions used during development and verification. Despite this requirement, a structured engineering process for defining target distributions and evaluating representativeness within ODDs remains largely unexplored. This work presents a method for representativeness assessment of AI/ML constituent ODDs in the context of aviation safety assurance. Starting from the methodical identification of suitable target distributions, a process flow is proposed that guides developers from ODD definition and parameter distribution modeling to the quantitative assessment and interpretation of coverage results with respect to EASA's learning assurance objectives. As quantitative measures, the chi-squared goodness-of-fit test is examined and found unsuitable for the large data sets arising in this setting, leading to the adoption of the Kullback–Leibler divergence and Cramér's $V$ for the representativeness assessment. The method is demonstrated using the example of AI-based airborne collision avoidance, employing experimental data from previous Horizontal Collision Avoidance System (HCAS) and Vertical Collision Avoidance System (VCAS) simulations. The results illustrate how statistical distribution comparison methods can support the assessment of representativeness for safety-critical AI applications and contribute toward a systematic Safety-by-Design AI engineering process aligned with emerging EASA guidance.
Read the full abstract ▾
All authors Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach
Artificial Intelligence
Chunhan Li, Chenglin Xu, Zongyang Zhang et al. (+8 more)
Evaluation of long-context Large
Language Models (LLMs) has advanced rapidly. However, most existing
benchmarks are limited to the document level and focus mainly on high-resource
languages, leaving many fine-grained challenges insufficiently evaluated. To address this gap, we present MGAL, the first
multilingual, granularity- and position-aware long-context
benchmark. MGAL is constructed from United Nations (UN) reports spanning 8K to 128K
tokens across the six official UN
languages. It covers four coherent levels of linguistic granularity (word, sentence, paragraph, and document) and further stratifies entries by their position within the document (begin, middle, and end), indexed at both the document and paragraph levels. This design enables systematic diagnosis of
multilingual long-context comprehension across different granularities. Through extensive experiments and analyses, we find that: (1) LLMs perform well at word-level tasks but struggle with coarser-grained ones; and (2) Closed-source models retain a clear performance advantage in lower-resource
languages. We further identify two new challenges: (1) Under local semantic crowding, where neighboring sentences share topics and entities, models tend to follow surface cues (e.g., connectives like “however” or repeated entities) rather than the discourse role of the sentence in surrounding context (e.g., background, outcome); and (2) A gap between fluency and consistency in generated outputs, where models produce text that reads smoothly but drifts from the source facts. In addition, we observe several patterns in line with prior studies, including reliance on nearby evidence and reuse of options under uncertainty.
Read the full abstract ▾
All authors Chunhan Li, Chenglin Xu, Zongyang Zhang, Jiale Liu, Zhuoxi Rao, Xudong Jia, Junxiu He, Menglin Yang, Wenjuan Gong, Zhengzhe Liu, Chengwei Qin
Artificial Intelligence · Cross-listed from cs.SE
BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERP
Haoran Sun and Klaus Marius Hansen
Agentic engineering systems have shown strong performance on general-purpose
benchmarks, yet their effectiveness in enterprise resource planning (ERP) domain-specific
languages (DSLs) remains underexplored. We introduce BC-Bench, a
benchmark designed to evaluate agentic engineering on real-world tasks in AL, the DSL for Microsoft Dynamics 365 Business Central. BC-Bench comprises 101 manually curated tasks extracted from two Microsoft-owned production repositories, reflecting authentic ERP development workflows. Adapting the SWE-Bench methodology, we address the unique constraints of the AL ecosystem—including limited public resources and complex environment provisioning. Beyond generating functional code, BC-Bench evaluates test generation and supports
multimodal problem statements where visual context is commonly present. We evaluate multiple frontier models across two
agent harnesses, utilizing multi-run metrics to account for nondeterminism. In the Bug Fixing category, under our evaluated settings, between-model differences in resolution rate are larger than differences between the two evaluated
agent harnesses, and improvements reported on general-purpose
benchmarks do not consistently transfer to AL. These results highlight the need for domain-specific evaluation.
Read the full abstract ▾
Artificial Intelligence
RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation
Kyle Wild, Yusuke Takahashi and Asako Uraki
Nearly every
retrieval-augmented question-answering system in production ships with a hidden interpreter: on each query a
language model re-derives the meaning of raw corpus text and then throws that work away. Cheaper models do not close the gap: per-
token prices have fallen by orders of magnitude while inference spend has risen, because context volume grows faster than prices fall. This is the modern equivalent of the full-table scan, and the remedy is the one databases found fifty years ago: do the expensive work once, at write time, into a maintained structure that makes reads cheap. A corpus whose read pattern is known before it ever meets a user can and should be indexed too. We call the paradigm ingest-time semantic compilation (ISC): compile a corpus's meaning into a queryable substrate with two coupled layers - incrementally maintained
embeddings, and atomic claims whose provenance is validated at compile time - and treat that substrate as a first-class database object with its own DDL, maintenance contract, migration contract, and cost model. Two existence proofs support it. Substrate upkeep scales with change rather than corpus size: incremental updates run 33.7x cheaper than reconstruction while tracking it to floating-point precision. And on a held-out sample of 500 broadcast-interview transcripts, compiled claims as the
retrieval payload win all 32 budget-by-model
cells: 85.2% correct from roughly 2.2k reader
tokens against 72.5% from 16.3k for the best chunk configuration anywhere. The only baseline that keeps pace is a contextualized-chunk pipeline with hybrid
retrieval and reranking, statistically indistinguishable from compiled claims at roughly twenty-one times the query-path
tokens - and it reaches that parity, we argue, precisely because it has itself begun to compile. We close with the systems agenda this opens, from compilation planners to read planning.
Read the full abstract ▾
Artificial Intelligence
TRACE: Agentic Catalog Enrichment with Multi-source Evidence Grounding
Rohan Kumar, Steven Xu, Kyle MacDonald et al. (+4 more)
Product catalogs underpin search, discovery, and recommendation in e-commerce, yet they are often attribute-sparse: the attributes shoppers and downstream systems rely on are either buried in unstructured content such as titles and images or missing from the catalog altogether. Manually enriching e-commerce catalogs is impractical given their scale and rapid growth. This paper introduces TRACE, a novel framework for automated catalog attribute enrichment using agentic Large
Language Models (LLMs). A ScoutAgent triangulates
multimodal evidence across merchant catalogs, syndicated feeds, and identity-matched web search to propose candidate attribute values with supporting evidence, while a JudgeAgent verifies the proposed value for each attribute value against its supporting evidence and decides whether to publish it or route it to human review. On an offline human evaluation
dataset, TRACE's proposed attribute values were 98.2% accurate at 74.7% attribute coverage. Deployed in production on an industry-scale catalog, TRACE increased impression-weighted enrichment coverage across four business verticals by 90.4%. An online experiment subsequently showed that surfacing the enriched attributes on the product detail page increased checkout conversion by 0.48%.
Read the full abstract ▾
All authors Rohan Kumar, Steven Xu, Kyle MacDonald, Matthew Long, Bernice Chow, Mac VanRenterghem, Sudeep Das
Artificial Intelligence
Foundation Models for Partial Causal Identification
Alexis Bellot and Anish Dhir
This paper investigates the development of causal foundation models for bounding the effect of interventions and counterfactuals from observational data. We show that a canonical prior can be defined with full support over the space of structural causal models with discrete observables. With this canonical prior, we translate the problem of bounding counterfactuals into that of learning distributions over functions that map data (and possibly structural assumptions) to a causal query of interest. This extends the promising causal foundational modelling paradigm to the estimation of partially-identifiable causal effects, i.e., under unobserved confounding, where multiple values are equally compatible with the observed data and prior structural assumptions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.plasm-ph
Advantage-level Aggregation Reinforcement Learning for X-point Target Magnetic Configuration Control in an EXL-50U Experiment-Calibrated Simulation Environment
Siqi Ding, Xuanhe Wang, Pei Guo et al. (+10 more)
Managing divertor heat loads is a central challenge for compact, high-power tokamaks. To increase local flux expansion and decouple the dissipation volume from the core, EHL-2 adopts the X-point target (XPT) divertor. This requires the secondary X-point to remain on the divertor leg; displacement degrades the
topology and exhaust geometry. Current experiments, including EXL-50U discharges, rely on precomputed feedforward waveforms with PID loops on global quantities. Lacking dedicated closed-loop feedback for the secondary null, XPT operation is repeatable but not routine. We formulate XPT feedback as a multi-objective reinforcement learning (RL) control problem in a free-boundary environment calibrated to EXL-50U discharge #13906. To address strong coupling among
plasma current, shape, and null constraints - where reward scalarisation collapses objective-specific temporal credit - we develop Advantage Aggregation (AdvA). AdvA preserves objective-wise temporal credit before worst-objective-aware nonlinear scalarisation and introduces a residual correction to policy updates. AdvA-PPO is evaluated against Reward-PPO and a feedforward-plus-PID baseline under nominal operation, measurement uncertainties, and unseen initial
equilibria. On a 500 ms rollout, AdvA-PPO raises the mean worst-channel score from 0.23 to 0.81 over Reward-PPO, reducing X-point flux RMSE by ~20x. Under combined measurement uncertainties, it is the only learned controller completing the horizon while retaining a usable XPT shape. Multi-initialization fine-tuning enables a single AdvA-PPO policy to complete full-horizon operation across divertor and limiter initial
equilibria. These results provide a simulation-based foundation for future real-time XPT validation on EXL-50U.
Read the full abstract ▾
All authors Siqi Ding, Xuanhe Wang, Pei Guo, Guoyang Shi, Changquan Yu, Yiting Wang, Xianming Song, Xiang Gu, Zhengyuan Chen, Lei Xing, Yapeng Zhang, Jianguo Chen, Tianyuan Liu
Artificial Intelligence · Cross-listed from cs.CL
STAR-OPD: Structured Aspect-Cascade-Aware On-Policy Reward Distillation for ABSA Quadruple Extraction
Tong Sun, Mingyang Ma and Jiayang Yu
Aspect-based sentiment analysis (ABSA) quadruple extraction requires jointly predicting target, aspect, opinion, and sentiment over reviews that often contain multiple fine-grained sentiment tuples. While large chain-of-thought (CoT) models perform well on this task, distilling them into smaller deployable models remains difficult. We identify a task-specific failure mode in distilled ABSA extraction: student errors at the target-aspect interface create structurally invalid states, such as broken target-aspect bindings and hallucinated targets, which then corrupt downstream predictions. Conventional off-policy
distillation is poorly suited to this setting because it trains only on teacher-generated trajectories and provides little supervision on the student-induced structural states that dominate inference. To address this mismatch, we propose
STAR-OPD (STructured Aspect-cascade-aware On-Policy Reward
Distillation), which builds on generic on-policy
distillation and instantiates it for ABSA quadruple extraction with cascade-aware, set-structured rewards.
STAR-OPD trains on student rollouts and applies set-structured rewards that directly target binding consistency, target grounding, and fine-grained aspect disambiguation. Experiments on E-ABSA20K and SemEval-2014 show that
STAR-OPD consistently outperforms off-policy and general on-policy baselines, reduces target
hallucination, and substantially improves performance on structurally hard cases. With Qwen3-4B,
STAR-OPD substantially narrows the student-teacher gap while improving inference efficiency, highlighting the importance of on-policy structural correction for distilled ABSA extraction.
Read the full abstract ▾
Artificial Intelligence
Prediction certification cannot replace explanation certification: a competence envelope for trustworthy AI under compound stress
Nataliya Shakhovska, Ivan Izonin and Stergios-Aristoteles Mitoulis
Artificial intelligence systems increasingly make consequential judgments - which patient is deteriorating, which building is safe to enter, whether an image is authentic and are trusted on the strength of how accurately and confidently they predict. The safeguards that certify them are correspondingly prediction-based: accuracy, calibration and conformal coverage all measure how well a model performs. Whether such checks are sufficient to establish model trustworthiness has remained unclear. Here we prove that they cannot. We establish a separation
theorem showing that a reliable model and a compromised one can be identical under every prediction-side certificate, including accuracy, calibration and coverage, yet differ arbitrarily in explanation fidelity and deployment behaviour. Detecting this failure requires access to the model's decision mechanism in addition to its predictions. We introduce the competence envelope as an operational framework that combines prediction and explanation certification into a single deployable criterion. Across diverse
datasets and model classes, the proposed framework reveals failure modes that prediction-side certification alone does not capture. Certification against failures that are invisible in prediction behaviour therefore requires evidence about the model's decision mechanism as well as its outputs.
Read the full abstract ▾
Artificial Intelligence
Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
Yang Liu, Bin Chong, Wenkai Yang et al. (+9 more)
Large
language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context. Existing certified robustness methods are limited to single-turn inputs; naive multi-turn composition yields bounds that degrade exponentially in the number of turns. We introduce Multi-Turn Certified Robustness (MTCR), a framework that models conversational safety via State-
Adversarial MDPs and defines $k$-turn certified robustness as the worst-case safety probability across $k$
adversarial turns. MTCR comprises: (i) compositional certification via
embedding-space mode decomposition, yielding tighter certified lower bounds than naive multiplication; (ii) $(\alpha,\beta)$-safety persistence, improving the degradation rate from $\underline{p}^{k}$ to $\beta^k$ (with $\beta > \underline{p}$) and yielding interpretable horizon estimates; (iii) matching information-theoretic upper bounds establishing tightness; and (iv) a unified
algorithm combining these results. Experiments on six LLMs under $\epsilon$-bounded and Crescendo-style attacks confirm that empirical safety consistently exceeds the certified bounds.
Read the full abstract ▾
All authors Yang Liu, Bin Chong, Wenkai Yang, Shuai Zhang, Yancheng Chen, Feiyu Han, GuoZhen, Cheng Zhang, Huaibing Xie, Changze Lv, Shihan Dou, Pluto Zhou
Artificial Intelligence · Cross-listed from cs.LG
Chenghao Li, Xiao Han, Xinxin Huang et al. (+22 more)
The
matrix-aware optimizer
Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large
Diffusion Transformers (DiTs) remain unclear. We first establish
Muon's scaling behavior on DiTs from 1.3B to 15B parameters, showing that its optimization and generative quality advantages over AdamW persist across model scales. However, at scale, the 5-step Newton–Schulz iteration (NS5) performed at every optimization step, together with full-momentum materialization, introduces substantial computation and communication overhead that can offset
Muon's step-efficiency advantage. We introduce Periodic Row-wise
Muon, which performs a full NS5 spectral update once every \(K\) steps and applies a low compute and communication cost row-wise constrained update based on the current momentum at the remaining steps. We further co-design a distributed implementation that operates directly on sharded momentum during non-refresh steps and accelerates spectral refreshes through bucketed all-gather and communication–computation overlap. Across all scales,
Muon improves the best observed generative quality over AdamW by 12.9–19.1%. Compared with vanilla
Muon, Periodic Row-wise
Muon remains within 0.5% in best generative quality on the 1.3B–4B models and improves it by 4.5% at 9B. It reduces optimizer time by 46.9–54.3%, end-to-end step time by 15.7–24.3%, and logical communication volume by 66.7%, while reaching its respective best generative quality with 33.7–64.8% less active training time. These results show that Periodic Row-wise
Muon preserves
Muon's generative quality advantage while translating it into end-to-end training efficiency for large DiTs.
Read the full abstract ▾
All authors Chenghao Li, Xiao Han, Xinxin Huang, Wei Liu, Boyang Li, Bing Xiao, Heran Zhang, Juanma Perez Rua, Ke Xu, Kangning Liu, Linjun Kuang, Na Li, Tan Wang, Tian Xie, Wei Peng, Yang Pei, Yifan Xu, Yuanhao Zhai, Yuwei Lin, Zhe Wang, Zihao He, Daniel Li, Junbiao Tang, Ziyang Jiang, Dake Chen
Artificial Intelligence · Cross-listed from cs.MM
When Images Look Right and Retrieve Wrong: Coverage-Guided Cross-Scale Re-Indexing for Knowledge-Faithful Generative Perception
Guangyuan Dong, Chuang Liu, Haoyu Wang et al. (+10 more)
Multimodal information systems increasingly route generated visual content back through the same
vision-
language index that informed its production, so the output must remain retrievable by the queries it was meant to serve. When the scene contains entities at vastly different scales, existing
language-guided generators condition on a single, globally pooled text
embedding and quietly drop scale-specific concepts, breaking concept-query
retrieval even when pixel fidelity is high. We formalise this failure as semantic collapse and propose CERES, a closed-loop
multimodal indexing framework that builds a three-level semantic pyramid, mines implicit concepts via a co-occurrence-aware router, performs scale-routed cross-
attention into a lightweight U-Net generator, and verifies coverage by re-indexing the generated image with the same frozen VLM. A continuously differentiable soft-Jaccard coverage objective returns dense gradients to the 0.39 M-parameter generator under explicit non-degeneracy conditions, and coverage is verified by an independent DINOv2 linear probe trained only on external scene and object labels. On four pansharpening
benchmarks across seven settings, CERES delivers the new state of the art with the largest gains where scale variation is most extreme (+4.64% relative Q2n and +9.7 mAP for DOTA detection). It also improves concept-query
retrieval Recall@5 by +14.0 points and image-text mean reciprocal rank by 0.19 over the strongest baseline, showing that the closed loop preserves queryable content rather than self-referential feature consistency.
Read the full abstract ▾
All authors Guangyuan Dong, Chuang Liu, Haoyu Wang, Yangchen Zeng, Jiaqi Zhang, Li Jiuxing, Xiaoyang Yu, Pinlong Zhao, Yuchao Hou, Ziwei Li, Zheng Lin, Alexander Lim Han Yang, Yusen Wu
Artificial Intelligence · Cross-listed from cs.CV
TRACE: Training-time Report-guided and Clinically Ordered Concept Editing
Wentao Yue, Tianyou Lai, Jiayu Luo et al. (+4 more)
Breast ultrasound diagnosis relies on clinically meaningful semantic concepts, yet most deep learning methods adopt end-to-end image-to-label paradigms that lack interpretability and robustness. While concept-based approaches offer a promising alternative, they often assume complete annotations or require
multimodal inputs at inference, which significantly limits their real-world applicability. To tackle these issues, we propose Training-time Report-guided and Clinically Ordered Concept Editing (TRACE), a training-time report-guided framework that leverages structured radiology reports as privileged concept supervision while enabling image-only diagnosis at test time. TRACE refines image-derived concepts through a teacher-guided editing mechanism within a malignancy-aware ordered concept space. To address incomplete annotations, we introduce Strategic Concept Missing Training (SCMT) and train an image-only self-editor via edit
distillation for autonomous concept refinement. Besides, we introduce BUSC, a concept-enriched
benchmark linking images, labels, and structured attributes. Experiments across multiple
datasets demonstrate that TRACE achieves superior performance and improved cross-domain robustness compared to existing methods.
Read the full abstract ▾
All authors Wentao Yue, Tianyou Lai, Jiayu Luo, Qingyu Mao, Ziying Wang, Zhenyuan Ning, Qilei Li
Artificial Intelligence
Neuro-Geospatial Modelling of EEG Affective States Using Literature-Informed Environmental Context
Utsav Poudel, Jagannath Aryal and Subramaniyaswamy Vairavasundaram
Environmental exposures such as air pollution and greenness have been associated with affective and cognitive outcomes, but
EEG and environmental
datasets are rarely jointly georeferenced. We investigate whether literature-informed environmental priors can serve as an auxiliary geospatial modality for
EEG-based affective-state classification when individual-level exposure data are unavailable. We combine 30-channel
EEG from the EAV
benchmark (42 participants, aged 20-30 years) with environmental representations derived from OpenAQ, Sentinel-2, Sentinel-5P, and OpenStreetMap data for Astana. A dual-tower architecture combines
EEG-Conformer representations with a graph-based environmental encoder. Because the
datasets are not co-registered, environmental context is treated as a literature-informed prior rather than measured exposure. Subject-level repeated splits, permutation and label-shuffling controls, dose-response reversal, and domain-shift experiments distinguish architecture-level gains from prior-dependent gains. The
multimodal model achieves 76.2% accuracy versus 67.4% for
EEG alone. Controls disrupting environmental-label structure retain part of this gain, indicating that the improvement is not attributable solely to environmental information. Replacing the Astana environmental distribution with an independently modeled Singapore distribution reduces accuracy to 72.8%. These findings demonstrate technical feasibility but do not establish an observed or causal exposure-affect association. The study provides a framework for future jointly collected mobile
EEG-environment studies. Implementation: https://github.com/r11up/geo-cog
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation
Yanglei Gan, Peng He, Run Lin et al. (+3 more)
Temporal Knowledge Graph (TKG) extrapolation seeks to infer future facts from time-varying relational histories. Recent
diffusion-based approaches improve uncertainty modeling through generative denoising, but their aggregated conditioning on subject histories may insufficiently distinguish query-specific evidence from non-salient historical facts, thereby diluting target-discriminative signals. To bridge this gap, we propose FreqDiff, a Frequency-aware
Diffusion framework for TKG extrapolation. Specifically, FreqDiff formulates future object prediction as query-slot denoising and develops a dual-stream denoiser that integrates temporal dependency modeling with context-aware spectral calibration. The spectral branch synthesizes history-conditioned filters from learnable bases to adaptively re-calibrate denoising representations, while a frequency-domain regularizer is proposed to align the denoised target with the gold object in spectral space. Experiments on four public TKG
benchmarks demonstrate that FreqDiff achieves state-of-the-art performance.
Read the full abstract ▾
All authors Yanglei Gan, Peng He, Run Lin, Peiyuan Jiang, Yifan Wang, Qiao Liu
Artificial Intelligence
SPARC: Single-Pass Scaling for Motion Forecasting with Conformal Bayesian Last Layers
Sakif Hossain, Julian Teusch and Jörg P. Müller
Human motion forecasters are increasingly accurate and fast, but reliable deployment requires uncertainty estimates that are structured, calibrated, and efficient.
Bayesian and ensemble-based uncertainty estimates often require repeated
stochastic inference [15, 26], while conformal calibration alone does not provide an epistemic signal or preserve trajectory covariance structure [14, 50]. We introduce SPARC (Single-Pass Adaptive Risk Calibration), a
Bayesian-conformal uncertainty layer for motion
forecasting. A deterministic MLP backbone predicts the future mean, and a conjugate
Bayesian last layer converts time-domain feature leverage into an analytic horizon-wise epistemic scale $\kappa_t(x)$. This scale inflates a graph-temporal Gaussian covariance without changing its correlation structure, and split conformal calibration produces 95% marginal prediction tubes with finite-sample validity under exchangeability. The key interface is the structured factorization $\kappa_t(x)\Sigma_{\mathrm{str},t}(x)$, which injects feature-space epistemic uncertainty into trajectory densities without Monte Carlo sampling. Across nine
dataset-protocol blocks and deterministic,
multimodal, and calibration baselines, SPARC ranks first on NLL and on the combined MPJPE+NLL criterion while retaining competitive point accuracy and efficient calibrated tubes. Ranking windows by $\kappa$ separates high-error cases, making the scale usable as a lightweight risk monitor.
Read the full abstract ▾