# Research Papers — 2026-09 · bundle page 211 of 266

> Full-text markdown of papers #10501–10550 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-09/page/211
[← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/210.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-09/page/212.md)

### IPM-FM: A Foundation Model with Consensus Feature Selection for Industrial Process Monitoring

Authors: Liang Cao, Weide Liu, Yan Qin, Jun Cheng, Weisi Lin, Bhushan Gopaluni
Published: 2026-09-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.08375v1

Industrial process monitoring is fundamental to the safety and economic performance of modern process plants. Current practice remains a one-task-one-model paradigm that is label-inefficient and prone to degradation under operating drift. Foundation models have reshaped language, vision, and generic time-series forecasting, but it has not been adapted to industrial process monitoring. This setting poses domain-specific challenges, including safety-critical decisions and asymmetric sampling between process variables and laboratory measurements. We propose the industrial process monitoring foundation model (IPM-FM). It first learns general-purpose representations from unlabeled industrial process data through self-supervised pretraining, then adapts to specific monitoring tasks using a small amount of task-labeled data, and finally produces calibrated predictions through an uncertainty-aware prediction head. IPM-FM integrates a self-supervised Informer backbone with a multi-criteria consensus feature selector, a recursive lag-feature regression head, and a calibrated Monte Carlo dropout uncertainty module. On a seven-year hydrotreater dataset for diesel flash-point soft sensing, IPM-FM attains an RMSE of 2.99, $R^2$ of 0.50, and 97\% coverage of its 95\% predictive interval, outperforming the strongest classical and from-scratch sequence baselines by 8.3\% and 14.6\% in RMSE respectively, supporting the viability of a unified pretraining--adaptation framework for industrial process monitoring.

---

### Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning

Authors: Tejasvi C. Addagada
Published: 2026-09-08
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2609.08373v1

Aligned language models fail under two independent pressures: the structural jailbreak class recently formalized as Involuntary In-Context Learning (IICL), which reframes a harmful request as the final missing cell of a data-labeling task completed by pattern rather than judged as content; and the erosion of safety alignment outside English. A natural hypothesis is that these compound. We test it directly. Using a deterministic IICL operator and a StrongREJECT-style rubric judge, we red-team two Google Gemini models on two benchmarks, a 30 general-harm behaviours from HarmBench and 30 financial-abuse behaviours from FinProof, each under a single-shot baseline and under IICL in four languages (English, Spanish, Hindi, Arabic). First, IICL generalizes to a second provider and is worse in finance: it lifts attack success from <=6.7% to 80-90% on HarmBench and 97-100% on FinProof, an order of magnitude above the <=24% its introducing study reported on OpenAI's GPT-5.4. Second, against the hypothesis, forcing the IICL output into a non-English language does not stack the two weaknesses, it attenuates the attack. Eleven of twelve non-English conditions score below their English baseline (sign test, p~0.003), the lone exception a ceiling tie near 100%; on the stronger model's financial set Arabic collapses from 100% to 33%. We attribute this to a relevance curse: once structure has unlocked compliance, the models produce lower-quality harmful content in lower-resource languages, which a substance-grading judge scores as partial. The pattern replicates under an independent non-Google judge (Cohen's kappa=0.86, 377 paired verdicts), and 76.6% of non-English responses were verified in-language. Jailbreak vulnerabilities are therefore not additive; the dominant residual risk is the English structural attack, most acute for financial abuse, not a multilingual one.

---

### Reading a Legal Question Word by Word: Embedding Trajectories of 2,144 Vietnamese Legal Headlines

Authors: Tran Minh Quan
Published: 2026-09-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.08372v2

A dense retriever encodes a question as one vector, but the question arrives one word at a time. We read 2,144 held-out headlines from Thu Vien Phap Luat (Vietnamese legal library) word by word with Nemotron-3-Embed 8B/1B and Qwen3-Embedding 8B/0.6B, encoding 65,444 prefixes against 20,034 articles, plus every prefix of 3,438 sub-questions from 1,112 multi-question headlines and of 168 answers. (i) The gold article becomes rank 1 after a median of 6-7 content words in every encoder, before the interrogative frame is read, and stays there to the end in 78-85% of cases. (ii) In a multi-question headline the lock is inside the first sub-question 94-98% of the time; the second leaves rank unchanged in 89-95%; encoded alone, the second reaches rank 1 in 42-58% vs 91-96% for the first, at the same lock word (95-97% identical). (iii) Numbers, dates and instrument identifiers move the embedding twice as far as content words and four times as far as interrogative words; 72-78% of steps move toward the gold article, and the closing interrogative frame moves against that direction in 95-99% of headlines. (iv) Rank/cosine clustering yields six archetypes (instant, typical, unstable, late, never-locking) that differ by legal area and form (chi-squared p < 1e-8): real-estate and litigation headlines never lock on a number; environmental and accounting headlines do so a third of the time. (v) An answer read word by word retrieves its article after 8-16 words and addresses the sub-questions in order asked in 83-89% of cases. (vi) A word's step keeps a consistent direction across headlines (cosine 0.25-0.33; 0.44-0.60 for numbers); a preceding question rotates that step by about 60 degrees and a greeting by about 30 degrees; steps shrink as i^{-0.8}; and a two-question headline is within 12-17 degrees of a linear mix of its two questions. We call this a context-modulated additive walk.

---

### Miles v0.1: Production-Level Post-Training

Authors: RadixArk, :, Tom Chen, Mao Cheng, Shi Dong, Kangrui Du, Yanbin Jiang, Jiajun Li, Yiming Li, Tao Lin, Yusheng Su, Andy Ye et al.
Published: 2026-09-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2609.08368v1

We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design of slime, Miles designs each stage of the reinforcement-learning (RL) training loop around a single principle: components should be verified, clean, and customizable. With accuracy, efficiency, reliability, and scalability as first-class goals, Miles aims to make frontier-scale RL accessible to researchers and enterprises alike. This report walks through the system end to end: rollout engines built on SGLang, a trainer with a choice of two backends (NVIDIA Megatron-LM and PyTorch FSDP), and three weight-synchronization transports for different deployment topologies. Beyond full-parameter RL, Miles also supports LoRA RL, on-policy distillation, supervised fine-tuning, and true-on-policy rollout-training alignment, and extends the same architecture to diffusion models. We close with an end-to-end case study: fully asynchronous agentic RL on a GLM-5.2 744B-A40B model over terminal-use coding tasks, running on 64 NVIDIA GB300 GPUs with a median step time of 263 seconds over the first 30 measured steps. Miles is open-sourced at https://github.com/radixark/miles, with the project website at https://miles.radixark.com.

---

### To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models

Authors: Siru Jiang, Yuwei Liang, Jian Liang, Ran He, Tieniu Tan
Published: 2026-09-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2609.08367v1

Test-time adaptation (TTA) has emerged as a prominent strategy for adapting vision-language models to distribution shifts during inference. We conduct a per-sample analysis of model predictions before and after adaptation, and observe two failure modes in existing TTA methods that echo previous work. Adaptations are frequently negligible, yielding no change in the model's predictions, and more severely, they can be detrimental by flipping previously correct predictions to incorrect ones. This naturally raises a question: Can we identify and skip such negligible or harmful adaptations? In this work, we introduce a new problem of selective adaptation, which aims to determine whether a given test sample should undergo adaptation or be skipped. To this end, we propose Cross-Augmentation Similarity (CAS), a simple baseline that performs adaptation only when predictions across augmented views exhibit low similarity. Notably, CAS not only preserves but in some cases improves overall accuracy, even when skipping nearly 85% of the adaptation process. We hope other researchers will explore this new direction and surpass the performance of our baseline. Our code is available at https://github.com/sirujiang/selective-adaptation.

---

### ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation

Authors: Yiran Wang, Zeyu Zhang, Ling Shao, Hao Tang
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08365v1

Text-to-motion (T2M) generation maps natural language to human joint movements, aiding gaming, VR, and robotics. Retrieval-Augmented Text-to-Motion (RAG-T2M) improves generation on complex descriptions by conditioning on retrieved motion-text pairs. However, existing RAG-T2M models face two challenges: coarse-grained retrieval and fusion mechanisms overlook the hierarchical, spatial-temporal topology of human motion, and a representation gap exists because retrieved evidence resides in a semantic space separate from the generator's latents. To address the first, we present ReMoMask, a structure-aware RAG framework coupling Hierarchical Bidirectional Momentum (HBM) contrastive learning to align global and part-level features with text; Semantic Spatial-Temporal Attention (SSTA) for topology-aware fusion; and Topology Structured Masking (TSM) to force robust part-level grounding via adaptive masking. To address the second, we introduce ReMoMask-2, which rebuilds the retrieval database directly within the generator's pre-quantization latent space and aligns text queries via a distilled lightweight projector, allowing the generator to directly consume the retrieved motion's semantic content. Extensive experiments on HumanML3D, KIT-ML, and SnapMoGen demonstrate our retriever achieves state-of-the-art accuracy, while ReMoMask-2 attains the lowest FID on KIT-ML and SnapMoGen; notably, its single mask-transformer stage surpasses ReMoMask's full two-stage pipeline and delivers the fastest inference.

---

### SentryLine: Evidence-Grounded Question Answering over Evolving Documents in Oncology Care

Authors: Tampu Ravi Kumar, Gaurav Najpande, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, Karan Kathuria, Shorya Azriel Moses, Yuvraj Kalia, M Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta
Published: 2026-09-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.08364v1

Oncology care operates at constant pressure of absorbing rapidly evolving evidence base in biomedicine. The American Society of Clinical Oncology (ASCO) addresses this through living guidelines, but the format introduces a new burden: any recommendation can change at any point, across multiple versioned documents. We present SENTRYLINE, a living guideline-aware clinical question answering system. SENTRYLINE retrieves guideline passages through a vectorless hierarchical RAG pipeline and returns a role-specific answer with inline citations, factual and temporal verification reports, and drift detection notes that surface when a guideline has been updated. We construct ASCOBENCH, a benchmark of 405 three-turn conversations across four question categories with gold answers from expert annotators(clinicians), and use test set to evaluate SENTRYLINE against five baselines under an LLM-as-judge framework. Experiments across three generation backbones show consistent improvements over four retrieval baselines and ASCO's guideline assistant, with particularly strong gains on Reasoning and Role-Specific questions where multi-hop synthesis and register adaptation are required

---

### RepoNav: From Snippet Retrieval to File-Centered Repository Navigation for Code Agents

Authors: Hongzheng Chai, Jiakun Li, Hongyue Yu, Yuan Yuan
Published: 2026-09-08
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2609.08355v1

Solving repository-level code tasks requires LLM-based agents to use code search tools to navigate large codebases and identify a small set of relevant files and functions. However, current retrieval tools typically return flat lists of isolated code snippets: such lists can surface relevant files, but provide insufficient structure for agents to distinguish the target function from semantically similar alternatives in the same file. We introduce RepoNav, a lightweight post-retrieval interface that reorganizes retrieved snippets into a file-centered navigation scaffold. By presenting compact structural cues and candidate targets, this scaffold guides on-demand file-structure browsing, helping agents compare sibling symbols before selecting a target function. Across diverse models on LocBench, RepoNav improves function-level localization and narrows the file-to-function gap. Controlled ablations demonstrate that these gains come from structured evidence organization rather than simply exposing additional file structure, and the approach also improves performance on a repository-level question-answering benchmark.

---

### Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent

Authors: Quang-Duy Tran, Trung Le, Bao Duong, Phuoc Nguyen, Thin Nguyen
Published: 2026-09-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.08354v1

Several geometry-aware approaches to low-rank adaptation have emerged for parameter-efficient fine-tuning of large pre-trained models. These methods aim to take full advantage of the geometric structure of low-rank manifolds for improving the efficiency in subspace utilization and reducing redundancy by enforcing orthogonality constraints during optimization. The strong empirical results of these techniques have motivated further study into whether predictions from such geometry-based adaptation methods could be overconfident. In this paper, we build on the singular value decomposition factorization of adapters to develop a framework based on Stein variational gradient descent (SVGD). In this formulation, the low-rank matrices are transported along the Stiefel manifold to match the targeted distributions while retaining their crucial geometric structure. Since this geometry-aware SVGD approach provides multiple solutions during inference, it supports uncertainty quantification and produces better-calibrated adapters on the Stiefel manifold. Extensive experiments show that our method delivers strong model calibration and attains higher prediction accuracy than SVGD and related uncertainty estimation methods that are formulated in Euclidean space.

---

### Segment Any Motion with Radar: Robust Multimodal Moving-Object Segmentation and Tracking

Authors: Jue Wang, Xuan Wang, Hao Zhou, Ruixiang Zhou, Yixuan Zhou, Tianshuo Yuan, Jieming Ma, Jie Zhang, Fei Luo
Published: 2026-09-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.08346v1

Moving-object perception must decide which image regions correspond to real motion and keep every instance identified over time. Methods that read motion from appearance, optical flow, or estimated trajectories lose that evidence under poor illumination, adverse weather, reflections, and occlusion. Radar is a natural remedy because it measures radial velocity directly instead of inferring it from photometric correspondence. However, existing benchmarks do not jointly provide radar measurements, dense moving-instance masks, and temporally consistent identities for surveillance. We therefore introduce RGBTR-Motion, a synchronized and calibrated fixed-camera benchmark that pairs RGB, thermal, and radar streams with dense instance masks and temporally consistent identities across diverse surveillance scenes. We also develop SAM-Radar, an RGB, thermal, and radar-based segmentation and tracking framework built on SAM 3. SAM-Radar's radar-aware detector fuses calibrated RGBT features with radar returns that are grounded at their projected image locations, and motion supervision, implemented as foreground classification of those projected returns, teaches the detector to reject clutter without any text prompt. The tracker associates accepted radar returns with individual trajectories and uses them as physical evidence that a visually degraded target remains present. This allows it to bridge short periods of low visibility or occlusion and reconnect a reappearing target to its existing identity instead of starting a new track. SAM-Radar attains 0.7027 IoU and 0.8090 F1-50, and raises MOTA, HOTA, and IDF1 by 0.2977, 0.1603, and 0.2857 over the strongest competing values.

---

### CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

Authors: Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu, Sreyas Mohan, Wei Ye, Dilin Wang, JQ Huang, Rakesh Ranjan, Aviral Chharia, Fernando De la Torre
Published: 2026-09-08
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2609.08345v1

Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotated 3D data. However, it produces thousands of redundant visual tokens whose cost grows with every view. Existing visual token pruners fall into two families, each limited in the 3D multi-view setting. Learned importance methods rank tokens by attention or encoder features; because redundancy here is fundamentally spatial, they keep near-duplicate tokens from a few prominent regions and leave most of the scene unrepresented. Voxelization methods improve spatial coverage but cannot enforce an exact token budget and saturate as multi-view observations overlap in 3D, capping retention well below the target. We show that spatial coverage is associated with 3D reasoning performance and introduce CoVeR, a deterministic, training-free selector that uses only token coordinates, with no learned signals. CoVeR selects tokens that collectively cover every region of the scene, and solves the limitations of both families: it enforces an exact per-scene budget, breaks the voxelization saturation plateau, and avoids the near-duplicate selections of learned importance. Extensive experiments show CoVeR outperforms prior SOTAs on all three 3D reasoning benchmarks and generalizes as a plug-and-play module tested across four VLMs. Notably, with only $\approx$8% of visual tokens, it preserves 93.5% of full-token performance, surpassing SOTA by 3.9 percentage points on average across benchmarks.

---

### VeriScene: Reconstructing Crime Scenes from Legal Evidence via World-Model Agent

Authors: Kevin Chuanpu Fu, Yongsen Zheng, Zee Kin Yeong, Kwok-Yan Lam
Published: 2026-09-08
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2609.08342v1

World models take multimodal inputs like text, photos, and diagrams to generate dynamic scenes in accordance with the laws of physics, thus opening a compelling application: fusing multimodal legal evidence to re-create a crime scene and re-enact how an offence could have been committed. However, feeding the raw, unorganized evidence into a world model fails in forensic use: it silently drops evidence, glosses over contradictory testimony, and produces motion that violates the evidentiary record. This paper presents VeriScene, an agent that orchestrates the world model: it reconstructs crime scenes from forensic photographs and witness statements of varying reliability, keeping every claim traceable to evidence and every motion physically plausible. VeriScene iteratively fuses the evidence into a cited narrative under an auditing loop, verifies the hypothesized dynamics via probe rollouts in the world model with corrective constraint injection, and renders the offence as a re-enactment video from a fused keyframe. On a benchmark of 25 crime scenarios across 7 physically-driven case types (139 forensic-style photographs and 65 statements with planted unreliability), VeriScene attains 0.9014 evidence coverage and 0.7217 factual consistency (0-1 scale) on the 20 test scenes, outperforming an end-to-end multimodal-LLM baseline by 20.35% in factual consistency and 34.88% in temporal coherence, while generalizing across four LLM orchestration backends at USD 1.82 per scene.

---

### TV-Regulated OPD: Direction Matters in On-Policy Distillation

Authors: Han Xiao, Yifan Niu, Dongyi Liu, Chang Luo, Jia Li
Published: 2026-09-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.08341v2

On-Policy Distillation (OPD) facilitates the transfer of knowledge from domain expert to student in the post-training phase of Large Language Models (LLMs). However, the supervision signals in mainstream OPD methods suffer from high variance and noise which is generally instable during training. In this work, we systematically investigated what really matters to the performance and the fundamental mechanisms behind the instability during training. We found that retaining only the sign of token-level advantages is sufficient to achieve the performance comparable to standard OPD. Meanwhile, smoother and bounded advantages can stabilize the training process without sacrificing its performance. These motivated us to shape the advantages using the Total Variation (TV) and propose a robust TV regulated On-Policy Distillation (TV-OPD) method. Benefiting from the bounded and diminished advantages, TV-OPD exhibits stable training dynamics and steady late-stage performance. We conducted comprehensive experiments and found that, across various settings, TV-OPD consistently achieved better performance and lower variance in the late-stage of training.

---

### RoboCousin: Build Your Own Simulation Playground for Robust Bimanual Robotic Manipulation

Authors: Jingxuan Zhu, Jingyi Li, LiangLiang Chen, Zhiyuan Jing, Jidong Zhang, Hongming Li
Published: 2026-09-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2609.08339v1

Bimanual manipulation policies require large and diverse training datasets, yet collecting demonstrations on physical robots is expensive and difficult to scale. Simulation can generate data efficiently, but existing pipelines typically operate within closed asset libraries and predefined scenes: adding a newly observed object or environment still requires substantial effort to reconstruct geometry, specify physical and semantic properties, annotate interactions, and integrate the result into executable tasks. We present RoboCousin, an extensible simulation-based data-generation platform that turns user-provided observations into reusable assets, scenes, and expert trajectories for bimanual manipulation. Built on RoboTwin~2.0, RoboCousin converts object images into simulation-ready assets with visual and collision geometry, semantic and physical metadata, and automatically generated grasp-contact candidates. It further constructs digital cousins that vary compatible objects, backgrounds, layouts, and language instructions while preserving task-relevant affordances and spatial relations. The same asset system supports tabletop and room-level scene construction, with collision-aware base control for interaction beyond a fixed workspace. We release RoboCousin-OBD, containing more than 3,000 annotated object instances and 50 background environments, and use RoboCousin to generate over one million expert trajectories across 50 tasks. Simulation and real-robot experiments show that the automatically generated interaction annotations are comparable to curated annotations, generated assets provide effective sim-to-real supervision, and tabletop cousins can improve transfer beyond training on a single reconstructed scene. RoboCousin therefore provides a practical path for expanding both the scale and coverage of synthetic bimanual manipulation data.

---

### A Multi-Modal Perception Pipeline for Object Detection and Tracking in Autonomous Racing

Authors: Davide Malvezzi, Michele Pestarino, Vittoria Cavicchioli, Valentina La Gamba, Silvia Severi, Fabio Bagni, Luca Bartoli, Massimiliano Bosi, Francesco Gatti, Micaela Verucchi, Ayoub Raji, Marko Bertogna
Published: 2026-09-08
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2609.08338v2

Object detection and tracking are fundamental components of perception systems for autonomous driving. Achieving robust performance under adverse conditions such as limited visibility, sensor noise, and failures remains an open challenge, particularly in autonomous racing, where vehicles operate at very high speeds, experience strong vibrations, and interact under small safety margins. This paper presents a multi-modal late-fusion perception pipeline for object detection and tracking in the autonomous racing domain. The proposed system extends previous work by exploiting all onboard sensors through a late-fusion approach and a dedicated multi-object tracking framework. Independent detections from cameras, LiDARs, and RADARs are combined to provide timely and robust state estimates of surrounding vehicles. The tracking method explicitly compensates for detection delays and embeds in its model prior knowledge of vehicle dynamics and track layout. Experimental evaluation on real-world data across diverse critical scenarios, representative of challenging edge cases also in urban driving, confirms the effectiveness of the proposed pipeline and its suitability to support safe and adaptive planning decisions.

---

### Distillation as Probability Transport: Routed On-Policy Distillation

Authors: Tianle Xia, Lingxiang Hu, Yiding Sun, Linfang Shang, Ming Xu, Lan Xu, Ning Zheng, Wei Xu, Jie Jiang
Published: 2026-09-08
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2609.08337v1

On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribution to scalar credit on individual tokens. Such credit indicates whether a token should gain or lose probability, yet leaves the corresponding redistribution unspecified. We recast OPD as teacher-guided probability transport and propose RouteOPD (Routed On-Policy Distillation), which decomposes local teacher--student disagreement into student-excess sources and teacher-deficit destinations and couples them into explicit transport pairs. RouteOPD optimizes pairwise log-odds toward jointly realizable targets obtained from a bounded teacher potential, while adapting the transport budget to the concentration of teacher demand. This formulation directs updates toward teacher-preferred destinations and controls their magnitude within a single transport operator. Experiments across four teacher--student settings and four mathematical-reasoning benchmarks demonstrate that RouteOPD consistently outperforms sampled reverse-KL OPD, with improvements accompanied by higher routing fidelity and lower background leakage. These results demonstrate the effectiveness of explicitly modeling probability transport in on-policy distillation.

---

### Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules

Authors: Weichi Yao, Cameron Gruich, Bryan R. Goldsmith, Yixin Wang
Published: 2026-09-08
Categories: physics.chem-ph, cs.LG, q-bio.QM
arXiv: https://arxiv.org/abs/2609.08333v3

Molecular size is coupled to composition, structure, and function, yet most 3D molecular generators require a predefined atom count. We introduce Equivariant-Free Transformer-Autoencoded Latent Flow Matching, a two-stage framework that samples a fixed-dimensional latent vector using flow matching and uses an autoregressive Transformer to determine molecular size, atom types, coordinates, and chemical attributes. Canonical atom ordering and rigid-pose alignment enable Transformers without equivariant layers, while decoded attributes guide bond reconstruction. On PCQM4Mv2, unconditional generation yields 87.9\% unique, novel molecules passing sanitization and PoseBusters checks, exceeding baselines with lower end-to-end training and sampling time and higher end-to-end throughput. Across ten target HOMO-LUMO gaps, internal ranking retains 30\% of screened candidates and increases the density functional theory-verified hit rate within 0.1 eV from 25.0\% to 52.4\%, while largely preserving novelty and diversity. These results demonstrate fixed-dimensional latent generation with autoregressive decoding as a practical approach to molecular design without prespecifying size.

---

### EdMCGS: Event-Driven Markov Chain Gaussian Splatting for Extreme-Low-Frame-Rate Dynamic Scene Reconstruction

Authors: Yuzhong Wang, Wenmin Wang, Xinxing Yu
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08332v1

We present EdMCGS (Event-driven Markov chain Gaussian Splatting), an end-to-end method for reconstructing dynamic 3D scenes from extreme-low-frame-rate RGB together with an event stream, which can then be rendered at any intermediate timestamp. Methods relying solely on RGB images generate numerous artifacts due to the lack of evidence from between consecutive frames. To supply this missing evidence, we model the scene motion as an event-driven Markov chain, in which the sparse RGB frames anchor the state at their own timestamps while the events recorded within an interval drive the transition across it. Since the transition reads the events of the current interval, it remains active at inference and produces the in-between motion of the 3D Gaussians directly from the events rather than by interpolation, which sets our method apart from prior work that uses events only as training-time supervision. The state is carried by a compact set of control points, each driven by the events sampled in the neighborhood of its own image projection, and a temporal local isometry term keeps the propagated motion locally rigid. Experiments on synthetic and real-world scenes show that EdMCGS outperforms both RGB-based and event-based baselines, while rendering in real time with far fewer Gaussians than the strongest event-based baseline. We release our source code and a new dataset at https://github.com/joseclipse/EdMCGS.

---

### Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?

Authors: Bangshuo Zhu, Wei Song, Yuxin Cao, Yuezhong Wu, Zhiquan Liu, Yuekang Li, Jingling Xue
Published: 2026-09-08
Categories: cs.CV, cs.CR
arXiv: https://arxiv.org/abs/2609.08331v1

Video Large Language Models (VideoLLMs) are increasingly deployed in safety-critical applications such as content moderation and video analytics. To process long videos efficiently, VideoLLMs rely on frame sampling, token compression, and modality fusion, which together form an observation pipeline that reduces the raw video to a compact internal representation. Recent observation-level attacks exploit this pipeline to prevent the model from perceiving harmful content, yet no defense has been explicitly designed for this threat. We introduce DefTEval, a controlled evaluation framework that systematically assesses whether input-level adversarial defenses, which operate on the pixel content of already-sampled frames, can mitigate observation-level attacks. Across five VideoLLMs, eleven representative defenses, and five attack types, we find that input-level defenses offer limited and inconsistent protection, with harmful detection rates frequently near zero. Critically, defenses fail even against attacks that embed harmful signals in every sampled frame, indicating that the bottleneck extends beyond sampling omission to the suppression of signals that do enter the model. Token compression discards localized features, and modality fusion systematically down-weights weakened visual signals. Furthermore, defense effectiveness is dominated by model architecture rather than by the defense method itself, and detection rates vary drastically across content categories, exposing structural weaknesses in temporal reasoning. These findings demonstrate that securing VideoLLMs requires system-level robustness mechanisms spanning sampling-aware coverage guarantees, token-level preservation of safety-relevant features, and modality-balanced fusion.

---

### EMBLEM: Enhancing Multi-script Table Detection through Masking

Authors: Dhruv Kudale, Udhay Brahmi, Ganesh Ramakrishnan
Published: 2026-09-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.08330v1

Table detection is a core task in document analysis, supporting downstream applications such as information retrieval, document reconstruction, and visual question answering. While existing deep learning models perform well on English and Chinese documents, they struggle with multilingual, multi-script documents due to script diversity and the limited availability of labeled data. To address this challenge, we introduce MANDALA (Multi-script Annotated Documents for Table Detection), a manually curated dataset of 2,323 table-containing pages spanning 18 languages and 15 scripts across diverse domains. We also propose EMBLEM, a masking-based paradigm for Multi-script Table Detection (MTD). EMBLEM generates masked images that conceal script- and font-specific details, enabling models pre-trained on abundant English documents to focus on script-agnostic page layout. Experiments across three table detection architectures show that EMBLEM consistently outperforms strong baselines on MANDALA while remaining competitive on five standard English-dominant benchmarks. Using only English masked images for fine-tuning, with no multi-script training data, EMBLEM achieves an absolute F1-score gain of 20.8% on MANDALA. We release MANDALA along with the accompanying code and models at https://github.com/IITB-LEAP-OCR/EMBLEM.git.

---

### Tracing Stereotypes from Representation to Output in Multilingual LLMs

Authors: Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen, Josef van Genabith, Koel Dutta Chowdhury
Published: 2026-09-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2609.08322v1

Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is represented or how it affects the output. To investigate these internal mechanisms, we compare linear probing, attribution patching, sparse autoencoders (SAEs) and feature ablation in Llama-3.1-8B, Qwen3-8B, and Gemma-2-9B. Probe performance peaks substantially earlier than attribution in all three models, with a separation of 36-53% of model depth. Retained Llama-Scope features often match the social category on which they were selected and form recurring semantic families, but their lexical alignment and ablation effects vary across SAE suites. Only 6-18% of evaluated residual-stream features have language-agnostic effects under our criterion, and none are category-agnostic. Language-agnostic features have larger mean ablation effects in Llama-Scope, but this pattern does not repeat in the other SAE suites. Decodability, output influence, and cross-lingual ablation effects therefore need to be measured separately.

---

### AttnCompress: Dynamic Attention-Guided Trajectory Compression for Software Engineering Agents

Authors: Zhengran Zeng, Yixin Li, Rui Xie, Wei Ye, Shikun Zhang
Published: 2026-09-08
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2609.08318v1

The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error nature of these agents generates lengthy interaction trajectories, creating severe bottlenecks in terms of context window limits and cost. While context compression offers a potential remedy, prior approaches suffer from static pruning strategies and granularity mismatches, often failing to preserve the semantic dependencies and syntactic details crucial for SE tasks. To strictly preserve critical task evidence while reducing context length, we introduce AttnCompress, a dynamic attention-guided trajectory compression framework. Unlike existing approaches, AttnCompress bridges the gap between semantic integrity and dynamic adaptability through three key mechanisms: (1) structure-aware segmentation via perplexity (PPL) spikes to preserve the syntactic structure of code and logs; (2) relevance estimation using proxy attention weights to quantify the precise relevance of historical blocks to the agent's current reasoning; and (3) a dynamic rolling window to re-evaluate and recall historical context as the task evolves. Extensive evaluation on SWE-Bench-Verified and Multi-SWE-Bench demonstrates that AttnCompress achieves a pass rate of 53.17%, outperforming prior state-of-the-art baselines while reducing token consumption by 21.6% and total costs by 33.6%. The framework proves to be model-agnostic and generalizes effectively across diverse programming languages.

---

### Supervised Cross-Modal Feature Alignment for Zero-Wearable Freezing of Gait Detection in Parkinsonism

Authors: Aryan Singh, Chandan Biswas
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08317v1

Objective assessment of Freezing of Gait (FoG) in Parkinson's disease (PD) relies predominantly on wearable Inertial Measurement Units (IMUs). While IMUs provide optimal kinematic precision, mandatory sensor attachment restricts continuous clinical deployment. Conversely, unobtrusive vision-based alternatives suffer substantial classification errors during turning-in-place tasks, where geometric self-occlusion degrades deterministic skeletal coordinates and obscures the high-frequency precursors required for FoG detection. To resolve these physical observation limits, we propose a supervised cross-modal subspace distillation framework. During optimisation, pre-trained kinematic data from IMU sensors and contextual clinical metadata act as oracles to guide a deployable visual architecture. By incorporating joint velocity and acceleration derivatives, utilising a confidence-based gating mechanism, the visual model mitigates some of the tracking errors during occlusion events. Empirical evaluations confirm this latent alignment transfers the predictive fidelity of hardware sensors directly into the visual representation, yielding $85.5\%$ accuracy, and $82.4\%$ balanced accuracy. All the while maintaining a vision only model at inference.

---

### From Glance to Scrutiny: Progressive Distortion Reasoning for Fine-Grained Image Quality Assessment

Authors: Aoting Zhang, Mingze Gao, Dongbao Yang, Longyi Chen, Daoxin Zhang, Yi Wu, Yao Hu, Yu Zhou
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08316v1

Multi-modal large language models (MLLMs) have demonstrated significant potential in image quality assessment (IQA) by bridging visual perception with descriptive evaluations. However, existing approaches mainly focus on holistic quality prediction, often functioning as black boxes that provide limited insight into where distortions occur and how they affect perceived quality, hindering fine-grained analysis of localized and heterogeneous degradations. We propose GS-IQA, a framework that reformulates IQA as a progressive Where--What--How diagnosis, emulating the human perceptual process from an initial glance to closer scrutiny. Since a severity judgment is meaningful only for a correctly localized and recognized region, we realize this progression through a two-stage reinforcement learning paradigm that respects such dependencies: the glance stage uses a perception-gated reward to establish where degradations lie and what they are, activating severity feedback only once both are correct, while the scrutiny stage introduces online reward-conditioned degradation generation to synthesize hard examples targeted at the model's perceptual bottlenecks, sharpening its discrimination of subtle severity variations. To enable systematic evaluation, we construct Diag-Bench, a region-level IQA benchmark of about 25K curated samples spanning 12 distortion types and five ordinal severity levels. Extensive experiments show that GS-IQA consistently surpasses state-of-the-art methods in distortion localization, recognition, and severity estimation, and that its diagnostic representations transfer effectively to conventional global quality prediction across diverse external benchmarks. Code and data will be released.

---

### Non-Coherent Over-the-Air Federated Learning: Protocol, Convergence, and Device Scheduling

Authors: Haifeng Wen, Nicolò Michelusi, Osvaldo Simeone, Yang Yang, Hong Xing
Published: 2026-09-08
Categories: cs.IT, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2609.08312v1

To mitigate the scalability bottleneck in the radio access network (RAN) in federated edge learning (FEEL), over-the-air federated learning (AirFL) exploits waveform superposition over multiple-access channels (MACs) for analog model aggregation. However, coherent AirFL typically relies on stringent PHY-layer conditions such as accurate channel state information (CSI), tight time/frequency synchronization, and frequent transceiver calibration for signal alignment. However, these requirements, if not impossible to be met, incur substantial communication and computation overhead. In this paper, we propose a non-coherent AirFL (NCAirFL) protocol over a broadband single-antenna MAC, leveraging binary dithering, unbiased non-coherent detection, and long-term error feedback to waive the need for instantaneous CSI. For NCAirFL with general smooth non-convex objectives and a constant learning rate, we establish a convergence bound achieving the convergence rate in the same order of $\mathcal{O}(1/\sqrt{T})$ as communication-ideal FedAvg, where $T$ is the total number of communication rounds. To further improve communication efficiency under data and wireless resource heterogeneity, we also derive a lower bound on the expected single-round objective decrease in the global loss conditioned on device scheduling, building upon which a surrogate objective function is obtained for jointly optimal device selection and power control. Experimental results on MNIST and CIFAR-10 corroborate that NCAirFL achieves learning performance close to FedAvg in practical settings, with the proposed device scheduling policy substantially accelerating convergence.

---

### Exploring Bottom-Up Clustering for Creating Semantic IDs

Authors: Leah Woldemariam, Sudhanshu Garg, Taha Belkhouja, Charles Kim-Yip, Ali Sahami
Published: 2026-09-08
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2609.08310v1

The success of generative retrieval has largely been attributed to the use of Semantic IDs, which improve over arbitrary item-level identifiers such as hashes by capturing the semantics of items. The main challenges faced when constructing Semantic IDs, however, is in mapping each identifier to a unique product and capturing information valuable to downstream tasks. Past works have appended additional codewords to de-duplicate item identifiers and utilized residual quantization to create hierarchical clusters. In this work, we present an algorithm for generating Semantic IDs that ensure the identifiers are both unique and preserve the structure of the original embedding. Key to our work is the use of bottom-up clustering to preserve local structure in the embedding space, improving the clustering quality of the resulting Semantic IDs and their utility for downstream generative retrieval.

---

### A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware

Authors: Maysam Khatib, Moysis Symeonides, Demetris Trihinas, George Pallis, Marios D. Dikaiakos
Published: 2026-09-08
Categories: cs.DC, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2609.08307v1

Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires balancing quality, latency, model footprint, and energy. This paper presents a controlled measurement study of self-hosted LLM inference across edge and near-edge deployment nodes: an NVIDIA Jetson AGX Orin and a near-edge server with CPU-only and GPU-enabled inference modes. We evaluate multiple open-weight LLMs and quantization variants using a fixed question-answering workload, and compare them against GPT-4o as a cloud-hosted accuracy and latency reference. Our benchmarking pipeline reports accuracy, model footprint, per-token decoding latency, prefill latency, and overall execution energy. The results show that GPU-enabled server execution provides the lowest compute-side latency, while Jetson Orin shows lower measured energy, consistent with its lower platform power under our setup. CPU-only execution is consistently dominated in latency for our workload and shows higher measured energy. We also show that parameter count and downloaded weight-file size alone do not reliably predict observed accuracy or latency. Finally, using Pareto-frontier analysis, we study how deployment decisions may change under possible streamed-token delivery overheads, highlighting that compute-side inference metrics alone can lead to suboptimal placement for latency-sensitive interactive web services.

---

### HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

Authors: Han Jin
Published: 2026-09-08
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2609.08306v3

We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside model memory or rebuild deception at the protocol layer, leaving the serving tier unprotected and feeding nothing back into detection. HoneyRoute couples (i) a streaming router (a frozen 0.8B-embedding backbone with per-domain MLP heads), (ii) a dual-implementation honeypot (a rule/prompt-engineered code honeypot or a dedicated same-family replica), and (iii) an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus, the router reaches F1=.911 at 38 ms median added latency, matching 96% of a two-tier guard-LLM cascade's F1 at 1/385 of its latency with 0% evasion under 13 adversarial transformations; diverting the malicious share cuts production-model token consumption under concurrent flooding with real GCG-suffix payloads by 97.8%; the trained replica agrees with the production model on 92.9% of benign holdout requests, while naive unconditional bait injection collapses to 7.6% and selective camouflaged injection recovers to 88.9%, mapping the recoverable fidelity-traceability frontier; and a loop-trained correction head cuts misrouting of legitimate security research 9x while raising detection F1 to .933.

---

### FPicker: Topology-Guided Evolution for Filament Tracing in Low-SNR Microscopy

Authors: Tingyin Zhao, Mingtao Huang, Yuan Shen
Published: 2026-09-08
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.08305v1

Automating filament tracing in Cryo-Electron Microscopy (Cryo-EM) is essential for 3D helical reconstruction but challenged by intersecting topologies and extremely low Signal-to-Noise Ratios ($\text{SNR} = σ_s^2/σ_n^2$ < 0.1 or -10 dB). Existing paradigms fail: pixel-wise segmenters suffer from severe topological fracturing, box-based detectors face ghost center drift, sequential trackers derail due to error accumulation, and traditional active contours collapse under artificial closed-curve constraints. To resolve these bottlenecks, we present FPicker, the first topology-guided framework reconciling these incompatibilities. It unifies perception via a center-endpoint representation and an open-curve evolution module to explicitly model non-cyclic connectivity. On simulated benchmarks, FPicker outperforms top baselines by over $40\%$ relative gain in mean spatio-angular precision (mSAP) and reduces topological gap rates by over $60\%$ under extreme noise ($-20\text{ dB}$). By learning intrinsic physical geometry rather than local texture, FPicker demonstrates strong potential as a resilient geometric backbone. Its zero-shot performance on the real-world EMPIAR dataset exhibits robust topological resistance, achieving a state-of-the-art 82.9\% mSAP upon fine-tuning. Our results also suggest modeling physical priors is a highly robust path toward bridging the sim-to-real gap in signal-starved scientific imaging. The code is publicly available at: https://github.com/tomzhaosky/FPicker.

---

### TRIUNE-Net: Harmonizing Scale, Shape, and Efficiency in Pancreatic Tumor Segmentation

Authors: Amir Hossein Saleknia, Alireza Kheyrkhah, Sanaz Karimijafarbigloo, Reza Azad, Sina Houshmand, Ulas Bagci, Dorit Merhof, Alaa Sulaiman
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08303v1

Pancreatic tumor segmentation in 3D CT volumes is challenged by extreme scale variability across both the pancreas and tumor, and highly irregular tumor morphology. While recent advances have pushed segmentation performance, existing methods do not explicitly address these challenges and come at the cost of excessive computational complexity, limiting their practicality in resource-constrained clinical environments. We propose TRIUNE-Net, a lightweight unified architecture that harmonizes scale, shape, and efficiency through three synergistic innovations. A multi-scale context aggregation module with stage-adaptive dilated convolutions enables the model to reason across the broad range of anatomical scales present in both organs. A serial linear-deformable attention mechanism combines large effective receptive fields with shapeadaptive deformable convolutions to capture irregular, non-convex tumor morphologies. Finally, an information-preserving downsampling module replaces conventional max pooling entirely, retaining all spatial information while adding negligible parameters, preventing small tumors from being discarded before they can be recognized. On both the MSD Pancreas and NVD Pancreas datasets, TRIUNE-Net achieves state-of-theart results with only 5.86 M parameters and no external pre-training, outperforming all baselines across all key tumor metrics. Specifically, it surpasses the next-best model by 0.45% in tumor Dice, 6.0 points in F1 score, 6.6 points in sensitivity, and 3.4 points in precision, simultaneously reflecting its ability to suppress both missed tumors and false alarms in clinically realistic conditions. Our code is available at: https://github.com/abdora-ai/TRIUNE-Net

---

### Human-Centric Image Captioning with Subject-Centered Spatial Understanding

Authors: Bozhou Li, Jiahang Zhang, Yue Ding, Yushuo Guan, Bohan Zeng, Yiyan Ji, Xinlong Chen, Yang Shi, Yifan Dai, Yuran Wang, Chengzhuo Tong, Pengfei Wan et al.
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08300v1

While multimodal large language models (MLLMs) achieve remarkable performance on generic image captioning, they frequently suffer from structural hallucinations in human-centric scenarios. Accurately modeling human subjects is foundational for critical downstream applications, such as accurate avatar/video/image generation and fine-grained human action understanding. However, these tasks require highly precise subject-centered spatial grounding, such as distinguishing egocentric left/right laterality and maintaining correct anatomical-object bindings. Although catastrophic for structural integrity, these localized spatial inversions are often overshadowed by overall descriptive metrics in existing benchmarks. To systematically expose and quantify this bottleneck, we introduce SPACE (Subject-centric Poses, Appearance, and Characteristics Evaluation), a benchmark designed to evaluate subject-centered spatial understanding. On SPACE, we reveal that despite strong generic perception, current MLLMs consistently fail to ground descriptions in the subject's intrinsic frame of reference. To bridge this gap, we propose a specialized data construction and alignment pipeline. We first extract structured spatial hints from fine-grained body-part localization to guide a two-stage caption rewriting process, yielding highly spatially-faithful training data. Furthermore, we design a rubric-based reward for Group Relative Policy Optimization (GRPO) that explicitly penalizes structurally critical spatial errors during alignment. Extensive experiments on SPACE demonstrate our framework significantly improves human-centric caption quality, particularly in subject-centered spatial reasoning, achieving performance competitive with strong closed-source models. Our benchmark and code are available at https://github.com/JHang2020/SPACE-Eval.

---

### LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Generation

Authors: Zijian Shen, Bin Zhou, Jiguang Wang, Ya Zhao, Jintao Ke
Published: 2026-09-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.08288v1

Travel survey data are essential for transportation planning and travel behavior analysis, yet collecting large-scale representative samples is costly and time-consuming. A practical alternative is to generate synthetic survey records from a few-shot sample. However, such samples provide incomplete coverage of heterogeneous traveler groups and insufficient evidence for recovering the complex dependencies between demographic characteristics and travel behavior. Existing approaches have complementary limitations. Probabilistic generative models such as Bayesian networks (BNs) offer explicit distributional control, but structures learned from few-shot samples may omit meaningful dependencies or retain spurious ones. Large language models (LLMs) can help address these difficulties in BN structure learning by providing behavioral knowledge that complements the limited statistical evidence. We therefore propose LEBGen, an LLM-enhanced BN framework that uses this knowledge to refine network structure for few-shot travel survey data generation. Specifically, the LLM first identifies traveler personas from demographic attribute and travel behavior statistics, then recovers dependencies missed by the persona-augmented BN structure and prune spurious ones. The refined BN is parameterized exclusively from the observed data to generate synthetic records. Under a 2% few-shot setting on the 2022 Hong Kong Travel Characteristics Survey, LEBGen reduces the mean marginal Jensen-Shannon divergence from 0.0671 to 0.0091 and the mean absolute Cramer's V error by 14.3% over the best-performing baseline, substantially improving both distributional and dependency fidelity.

---

### HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting

Authors: Namwoo Kim, Hyungryul Baik, Yoonjin Yoon
Published: 2026-09-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.08286v1

Multi-scale modeling has become an effective approach for long-term time series forecasting, capturing temporal patterns that range from fine-grained local dynamics to coarse global trends. Representations across these temporal scales are inherently hierarchical, with coarser scales abstracting and aggregating information from finer ones. While existing approaches readily exchange information across these scales, the hierarchy itself is typically left as an emergent byproduct of such interactions rather than captured as a geometric structure in its own right. In this paper, we introduce HypLTSF, a framework that endows the multi-scale hierarchy with a concrete geometric form by embedding scale-wise representations into the Poincaré ball, whose exponentially expanding volume naturally accommodates hierarchical structures. To align this geometry with the temporal hierarchy, HypLTSF imposes two constraints: (1) a radial constraint that orders embeddings by their level of abstraction, and (2) an angular constraint that groups fine-scale patterns sharing a common coarser-scale ancestor. Extensive experiments on long-term time series forecasting benchmarks show that HypLTSF achieves state-of-the-art performance, suggesting that explicitly modeling the multi-scale hierarchy as a geometric structure is effective for forecasting.

---

### MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation

Authors: Nagito Saito, Shintaro Ito, Koichi Ito, Takafumi Aoki
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08283v1

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in zero-shot transfer but often struggles with dense prediction tasks due to low spatial resolution and the loss of structural information. To address these limitations, we propose MARS-CLIP (Multi-resolution and Attention Refined Segmentation for CLIP), a novel framework for zero-shot semantic segmentation. Our approach introduces two key strategies: (i) a multi-resolution feature extraction module that fuses local fine-grained features with global context to overcome input resolution constraints, and (ii) an attention refinement mechanism that injects spatial and color biases from intermediate layers into the final self-attention block to accurately restore object boundaries. A set of experiments on six public datasets demonstrates that MARS-CLIP significantly outperforms state-of-the-art methods.

---

### Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models

Authors: Ke Hao, Yuanzhi Liang, Tingxi Chen, Rui Li, Haibin Huang, Chi Zhang, Yun Gu, Xuelong Li
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08282v1

Unified multimodal models integrate visual understanding and generation within a single network, yet the two capabilities are commonly optimized as separate tasks. We introduce Generative Grounding Feedback(GGF), a self-evolving post-training framework that uses only text prompts and the model's own visual experience. Given a prompt, the model first generates a visual ``dream.'' Flow-level feedback compares text-, image-, and repair-conditioned predictions at the same noisy latent state, transferring image-grounded generation directions to the prompt condition. Dream replay grounding replays this dream through captioning and re-imagination, training claim-level evidence to remain consistent across the replay while separating unrelated visual experiences. Jointly optimized, these two directions let generation provide visual grounding for understanding and understanding refine subsequent generation without paired image--text supervision. Experiments across unified models with different understanding--generation integration designs show consistent improvements in text-to-image generation together with modest gains in visual understanding.

---

### SAM3-O2D2: Zero-Shot Object Out-of-Distribution Detection by Object Class Prompting of the SAM3-Image Model

Authors: Lucas Görnhardt, Timo Bartels, Tim Fingscheidt
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08281v1

Object detectors have shown remarkable performance in various fields, among these medical imaging, surveillance, and autonomous driving. However, they are prone to overconfidence when encountering unseen objects in real-world deployments, causing potential safety issues. To address this, detecting out-of-distribution (OOD) objects is essential for reliable object detection. Modern approaches leverage the broad semantic knowledge of foundation models such as CLIP for post-hoc few- and zero-shot OOD detection. However, these methods typically perform OOD assessment in feature space, which can be sensitive to object detector localization errors and variations in object appearance. Moreover, the current state-of-the-art (SOTA) zero-shot method performs computationally costly diffusion in inference. In this work, for our proposed zero-shot object OOD detection method SAM3-O2D2, we employ the SAM3-image foundation model in an efficient manner. Specifically, we prompt SAM3 only with the object detector's predicted classes and compare the predictions of the object detector and SAM3. An object is in-distribution (ID), if SAM3 also detects an object at the corresponding location. If SAM3 does not detect the prompted object, this indicates a mismatch between the detector's prediction and the image content, suggesting that the object is OOD. Experimental results show that our method significantly surpasses the so-far zero-shot SOTA method. Specifically, we achieve new SOTA AuROC and FPR95 metrics over both ID datasets Pascal-VOC and BDD100K and both OOD datasets MS-COCO and OpenImages.

---

### What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory

Authors: Chen Shen
Published: 2026-09-08
Categories: cs.CL, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2609.08279v1

Agent memory systems must discard stored information when their history exceeds a fixed token budget. Existing budget-accuracy frontiers quantify the resulting loss in accuracy, but do not distinguish irreversible losses caused by eviction from recoverable retrieval failures. We introduce the restore counterfactual, a per-question paired intervention that reinstates the question's gold evidence in the read-time context and reruns the same reader. Combining the change in correctness with whether the evidence was retained after eviction classifies each oracle-answerable error as recoverable, irreversible, or residual; in the residual case, the answer remains incorrect after restoration. We evaluate FIFO, random, redundancy-aware, and LLM-importance eviction on LongMemEval-S at three budgets and under two retrieval regimes, using GPT-4o-mini as the primary reader and judge and GPT-5.4-mini as a robustness reader. Under top-k retrieval at an 80k-token budget, the irreversible share among errors corrected by restoration is 0.67-0.73 for FIFO, random, and redundancy-aware eviction, compared with 0.60 for LLM-importance. At 8k tokens, it reaches 1.00 for all four policies. Recoverable errors occur under top-k retrieval at 80k tokens but are absent under forced-gold injection by construction, so budget-accuracy results are not directly comparable unless the retrieval regime is reported. An exploratory matched-accuracy analysis detects no difference in irreversible rate among accuracy-matched policy pairs at a resolution of 1.2-6 percentage points. The same analysis detects the deliberately destructive control. To our knowledge, this is the first per-item, per-question restore-counterfactual audit of eviction for external agent-memory stores on a standard conversational benchmark.

---

### Adaptively Incorporating Directional Hints into Zeroth-Order Optimization

Authors: Alexander Ryabchenko, Jian Qian, Wenlong Mou
Published: 2026-09-08
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2609.08277v1

We study zeroth-order optimization of non-convex functions with the aid of directional hints, which are cheap but potentially inaccurate approximations of the true gradient direction, given by linear subspaces at each iteration. To leverage these hints adaptively while maintaining robustness to their quality, we introduce Control-Variate Zeroth-Order Descent (CV-ZOD), a new framework that refines the classical zeroth-order gradient estimator with a control variate that can be set based on the directional hints. We first show that the oracle algorithm that optimally sets the reference vector and step size at each iteration achieves a convergence rate that interpolates between the first-order $O(1/T)$ rate and the zeroth-order $O(d/T)$ rate, depending on the quality of the hints along the trajectory. We then develop a practical variant of CV-ZOD that achieves the same oracle guarantee up to logarithmic factors, without any prior knowledge of the hint quality. We validate the method empirically on simulation-based scientific optimization tasks, demonstrating sustained progress on non-convex landscapes where zeroth-order descent is slower and existing guided methods stall as guidance deteriorates.

---

### Online Signature Verification Using Augmented Path Signature and T-Mamba

Authors: Ruiling Li, Danyu Yang
Published: 2026-09-08
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2609.08276v1

Handwritten signature verification is vital for personal authentication across commercial and financial applications. Although deep learning methods are widely adopted for online signature verification (OSV), they often struggle with capturing highly discriminative features and modelling long-range dependencies. To address these issues, we propose a novel framework that integrates the augmented path signature (APS) descriptor with the T-Mamba model. The APS descriptor first applies time and basepoint augmentations, then computes sliding-window path signatures. The path signature is a non-parametric feature map from rough path theory that effectively captures geometric structures and nonlinear inter-channel interactions. Inspired by the efficacy of state space models (SSMs) in sequence modelling, our T-Mamba model employs a hybrid design combining two temporal convolutional network (TCN) blocks with a time-scanning Mamba. This design enables the model to learn both local temporal patterns and global long-range dependencies, substantially improving verification accuracy. Our framework achieves state-of-the-art EERs on three public benchmark datasets (MCYT-100, SVC-2004 Task 2, DeepSignDB), validating its effectiveness and robustness, especially when the training data is limited. Our code is publicly available at https://github.com/DLRL04/OSV-using-APS-and-T-Mamba.

---

### Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation

Authors: Tianyi Zeng, Junchao Liao, Yujie Wei, Ziying Zhang, Litao Li, Tianyi Wang, Zhichao Wei, Shuyao Xu, Wenwen Qiang, Siyu Zhu, Zhenghao Zhang, Long Qin
Published: 2026-09-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.08275v2

Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Professional editing depends on shot structure, transition grammar, audio-video cut relations, and montage, yet existing benchmarks largely rely on proxies such as content quality, synchronization, or physical plausibility, systematically missing whether such editing instructions are actually executed. We introduce CutCraft, the first benchmark for editing-technique execution in multi-shot audio-video generation. CutCraft extends structured multi-shot prompts with explicit editing specifications and is paired with a hierarchical hybrid evaluation framework that combines shot-structure alignment, expert-model metrics, tool-grounded multimodal judgment, and rubric-based question answering. Beyond evaluation, we design an agentic editing baseline that decomposes generation into planning, shot-level synthesis, and post-hoc composition, explicitly realizing editing semantics such as J-cuts, L-cuts, and transition timing. Across 13 state-of-the-art closed- and open-source models, CutCraft reveals a consistent gap between coherence and editing-technique execution: current systems often produce plausible multi-shot videos yet fail to execute editorial instructions reliably. We find unstable shot structures, weak control of transition execution, and sharp degradation on higher-order montage, while aesthetic quality is only weakly correlated with editing-technique compliance. The benchmark and metrics, and the editing agent baseline are available at https://github.com/AlibabaResearch/cut-craft-bench.

---

### MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

Authors: Junxi Wang, Te Sun, Jiayi Zhu, Chen Zhang, Siyuan Li, Xuyang Liu, Zichen Wen, Xiaobing Tu, Jinkui Ren, Xiantao Zhang, Ziqi Yuan, Linfeng Zhang
Published: 2026-09-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.08273v1

Agent memory systems have demonstrated significant potential in long-term dialogue, personalized assistants, and video understanding. However, continuously accumulated memory introduces substantial storage and retrieval costs during inference. To address this issue, we propose \textbf{MemForest}, a general memory compression framework adaptable to various agent memory systems. Specifically, MemForest partitions historical memory into event-centric units by leveraging global semantic similarity and local temporal continuity. For each unit, it constructs a maximum spanning tree, termed an EventTree, and progressively merges redundant memory nodes by selecting high-weight edges, reducing storage overhead. Furthermore, we introduce an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy. Extensive experiments demonstrate the effectiveness of MemForest. Under the unimodal Mem0 framework, MemForest retains \textbf{97.1%} of the original performance while compressing \textbf{50%} of historical memory across three benchmarks (LoCoMo, LongMemEval, and PersonaMem), achieving a \textbf{1.89x} retrieval speedup. Under the multimodal M3-Agent framework, it preserves \textbf{99.7%} of the original performance with a \textbf{50%} compression ratio across two benchmarks (M3-Bench-robot and M3-Bench-web), achieving a \textbf{2.24x} retrieval speedup. \textcolor{RoyalBlue}{\textit{Our code is available at (https://github.com/Celina-love-sweet/MemForest.}})(https://github.com/Celina-love-sweet/MemForest.}})

---

### Three Types of Negation of Triple and its Elements and an Extension of Triple

Authors: Zhenghua Pan
Published: 2026-09-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.08271v1

In various data models, the classical triple is a typical semantic data model. However, due to the design of the triple as a simple structure for representing positive assertions, it cannot sufficiently express different forms of negation present in the triple and its elements. This paper conceptually proposes that there are three distinct forms of negation within triples and their elements: contradictory negation, opposite negation and intermediary negation. Based on the the set SCOI and the logic LCOI+PLCOI with three kinds of negation, we propose an extension of triple that can distinguish and express these three different negations in the triple and its elements, called the TCOI triple with contradictory negation, opposite negation and intermediary negation. The TCOI triple is a semantic and structural extension of the classical triple. While retaining the ability to express positive assertions, it systematically introduces the three semantic dimensions of three negations, allowing these negations to independently act on the elements of the triple and on the whole triple. This significantly enhances the triple model capability to represent and reasoning about complex negative information. This paper also explores the expressive power and reasoning of the TCOI triple, as well as the application of TCOI triple implication reasoning in counterfactuals and counterfactual reasoning. We propose a truth-value (continuous value) algorithm for TCOI triple implication reasoning and perform its calculation through an example of the counterfactuals and counterfactual reasoning.

---

### Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding

Authors: Namwoo Kim, Jeeyun Chang, Kanghoon Lee, Yoonjin Yoon
Published: 2026-09-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.08268v1

Urban region embeddings have shown promising results in diverse urban sensing tasks such as crime, income, and service-call prediction. Recent methods improve representation quality by integrating mobility data with auxiliary modalities, using cross-view attention or contrastive objectives to align heterogeneous features into a unified region representation. However, leveraging the temporal dynamics of human mobility remains under-explored. Regional inflow and outflow fluctuate throughout the day, and inter-region connections emerge, persist, and dissolve over time. Moreover, prevailing fusion strategies combine views additively and miss the joint signal that emerges only when views co-occur. To address these gaps, we propose Mobility Stream-Structure Synergy (MoSS), which derives complementary views from mobility data: a Sequence view that preserves each region's hourly inflow/outflow profile, and a Structure view based on zigzag persistence diagrams that capture how regional connectivity emerges, persists, and dissolves over time. A synergy module then extracts emergent representations from the co-occurrence of these views through multi-degree interactions, explicitly capturing higher-order signal across views. Extensive experiments on New York City and Chicago show that MoSS achieves state-of-the-art performance across three downstream tasks using mobility data alone, outperforming baselines that rely on auxiliary modalities.

---

### Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation

Authors: Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang
Published: 2026-09-08
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2609.08267v1

Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations, retrieval-augmented generation (RAG) has emerged as a promising solution by retrieving relevant evidence at inference time, grounding outputs beyond the model's parametric knowledge. In this paper, we target a critical and practical learning problem RAG-based hallucination detection (RHD), where RAG is employed to enhance hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust alignments under evidence perturbations. Experiments across multiple RAG benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.

---

### Tracking-by-detection in Multi-object Tracking: Survey and Experiments

Authors: Yujin Yang, Kyujin Shim, Kangwook Ko, Changick Kim
Published: 2026-09-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2609.08265v1

Multi-object tracking (MOT) is an essential computer vision task that simultaneously tracks multiple objects in video sequences, with various applications in surveillance, autonomous navigation, and human-computer interaction. The tracking-by-detection (TBD) paradigm, which combines object detection with temporal association, has emerged as a leading approach, driven by innovative algorithms. Despite recent progress, fair evaluation of TBD-based methods remains a challenge. Many studies introduce modules such as similarity metrics, data association strategies, or motion models, but they are often evaluated under inconsistent protocols, with different baseline trackers, hyperparameters, and datasets. Such inconsistencies obscure the genuine contribution of each module and hinder objective comparison. This survey systematically reviews TBD-based MOT techniques, including similarity measurements, data association, camera motion compensation, and interpolation strategies. Starting from a minimal baseline tracker, we fairly evaluate the contributions of each method across diverse datasets and accumulate well-balanced methods. Our findings establish a strong baseline tracker and provide a foundation for the principled design of robust and versatile MOT systems suitable for real-world deployment.

---

### Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems

Authors: Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Published: 2026-09-08
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2609.08258v1

Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact is marked invalid and retained rather than deleted. However, whether that mark is enforced at retrieval time is unexamined. In this paper, we measure five such systems: we load each with a revoked policy and its replacement, track whether the revoked fact is returned at retrieval and whether the agent then acts on it across nine policy scenarios and nine models, and score every trial under six defense conditions. We find that no system enforces revocation by default: the revoked fact is returned wherever the revocation label is visible to the retrieval layer, outranks its replacement, and leads agents to the unsafe action. Based on these findings, we develop a guard that sits between the agent and any memory backend and withholds records that are revoked or conflict with their replacement.

---

### ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing

Authors: Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Published: 2026-09-08
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2609.08256v1

Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built and tested in isolation, and the resulting scores are hard to trust. To tackle this, we present ACEA (Adversarial Co-Evolution Arena), a platform that connects a pluggable red-team adapter and a pluggable blue-team adapter to a shared target LLM and scores their attack and defense rates with an LLM judge. ACEA contributes four components. First, a pluggable, model-agnostic arena. Any red or blue project connects over a minimal HTTP protocol, which we call the ACEA Standard Adapter Protocol (ASAP). It can be written in any language, and a project that exposes nothing but the protocol is a full participant. Second, an evaluation methodology built for adversarial rounds. Seeding the target with canonical secrets gives verifiable ground truth that separates real leakage from hallucination. We also send each attack to the target even when the defense blocks it, which measures the attack's raw potency independently of whether it was stopped. Together these yield a per-round decomposition of attack strength and defense effectiveness. Third, a real-time, game-style visualization with a detailed end-of-battle report that localizes each failure. The evaluation thus becomes an actionable signal for improving a red or blue project. Fourth, an optional in-context improvement loop that turns each round's outcome into advisory hints for the next. An adapter can then adapt across rounds without keeping state, provided it reads the hints. We describe the design of ACEA and the metrics through which red and blue teams are scored head to head.

---

### CircuTutor: Transforming Static Circuit Problems into Intelligent and Dynamic Tutoring

Authors: Ziyu Luo, Xiaorui Ma, Lin Chen, Xiaoming Chen
Published: 2026-09-08
Categories: cs.AI
arXiv: https://arxiv.org/abs/2609.08254v1

Learning direct current circuit concepts requires learners to connect invisible physical quantities, such as current, voltage, resistance, and power, with observable outcomes such as bulb brightness. Conventional textbook materials and general-purpose circuit simulators provide opportunities for problem solving and exploration but offer limited support for explaining why circuit behavior changes or diagnosing the reasoning behind incorrect answers. We present CircuTutor, a circuit-state-driven intelligent tutoring system that transforms static textbook circuit problems into an interactive tutoring workflow. CircuTutor first uses multimodal problem parsing to extract the textbook question, circuit topology, component parameters, switch states, and answer options, which are converted into a structured task and validated through circuit simulation. Learners can then interactively explore the circuit (by changing parameters) and submit an answer while a SPICE-compatible solver computes physically consistent circuit states. After the learner submits an answer, CircuTutor presents a before-and-after circuit state animation corresponding to the selected operation, organizes the simulated state changes into a causal reasoning chain that explains the underlying circuit behavior, maps answer discrepancies to likely misconceptions, and generates adaptive follow-up exercises targeted at the diagnosed misconception. Our experimental results demonstrate that CircuTutor effectively improves conceptual learning and the overall learning experience. The proposed framework demonstrates how simulated circuit states can be transformed into intelligent and interactive tutoring for circuit education, with the potential to generalize to other STEM domains.

---

### Revisiting Spectral Representations in Generative Diffusion Models

Authors: Yuehao Wang, Peihao Wang, Hanwen Jiang, Ziyi Yang, Qixing Huang, Zhangyang Wang
Published: 2026-09-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.08253v1

Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks can both facilitate training convergence and enhance sampling quality, yet the mechanism driving this synergy remains insufficiently understood. In this paper, we investigate the connection between self-supervised spectral representation learning and diffusion generative models through a shared perspective on perturbation kernels. On the diffusion side, samples (e.g., images, videos) are produced by reversing a stochastic noise-injection process specified by Gaussian kernels; on the spectral representation side, spectral embeddings emerge from contrasting positive and negative relations induced by random perturbation kernels. Motivated by this, we propose a self-supervised spectral representation alignment method to facilitate diffusion model training. In addition, we clarify how joint spectral learning can benefit diffusion training from a geometric perspective. Furthermore, we find that the optimization of the spectral alignment objective is in an equivalent form of diffusion score distillation in the representation space. Building on these findings, we integrate a spectral regularizer into diffusion training objectives to improve the performance of diffusion models on multiple datasets. Experiments across images and 3D point clouds show consistent gains in generation quality. Code is released at https://github.com/yuehaowang/spectral-reg-diffusion.

---

### CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations

Authors: Aman Mehta, Riya Baviskar
Published: 2026-09-08
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2609.08250v1

How far a pushed object slides depends on its mass and friction, which no single image reveals. Pretrained visual encoders are increasingly used as the perception front end of world models for manipulation, and their physical competence is assessed with perturbation benchmarks and linear probes, almost always in a clean, fixed-camera scene. We show that these assessments cannot distinguish an encoder that infers physics from one that does not. CALIPER (calibrate, then predict) is a direct test: an object of unknown mass and friction is struck twice at known speeds, a third strike is shown only up to the moment of contact, and a linear readout on frozen features must predict how far the object slides. Swapping in another object's calibration clips checks that the evidence is actually used. Across 2,000 simulated episodes and eight representations, from V-JEPA 2 to a randomly initialised ViT and raw pixels, calibration adds +0.50 R^2 and the swap removes it. Yet in the clean scene every representation lands within 0.02 R^2 of the ceiling set by true simulator state, because a fixed camera exposes the object's displacement directly in pixel coordinates. Resampling camera, lighting, and clutter for every clip spreads the same representations across 0.50 R^2; when the readout chooses a push speed for a goal distance, V-JEPA 2 misses by 4 mm and the random ViT by 20 mm, no better than ignoring the object. Linear probes track none of this: a change in frame aggregation moves a probe more than pretraining does, and erasing the probed mass direction from the same representation costs nothing in one scene and 0.35 R^2 in the other. Whether a benchmark can rank models is an empirical property, and we give three checks that establish it.

---