# Research Papers — 2026-10 · bundle page 107 of 156 > Full-text markdown of papers #5301–5350 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/107 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/106.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/108.md) ### Post-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation Error Authors: Iván Verdugo Guerra, Ezequiel López Rubio, Jorge García González Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08756v1 The same Gaussian of a 3D Gaussian Splatting model is seen from many views, and these views do not always agree on the class it belongs to. The Gaussian may be occluded in some of them, and the confidence of the detector is not the same from one view to another. The ground truth, on the other hand, is given as an annotated mesh, because two training runs do not produce the same Gaussians. In this work, we propose a post-training lifting method that works with one target class at a time and combines the information coming from all the views. Target and non-target evidence are accumulated simultaneously, weighted by the visibility of each Gaussian in each view. After that, the Gaussians are filtered with two thresholds: a main threshold $β$ selects the high-confidence seeds, and a lower one $γβ$ adds the connected components around them. For the evaluation, the labels are transferred from the Gaussians to the mesh vertices that are both visible and annotated. With this design, we can separate three sources of error: the 2D detector, the lifting and the transfer between representations. The thresholds and the transfer operator are chosen on seven Replica validation scenes, and the method is evaluated on ten held-out ScanNet++ scenes with the same values for every scene and class. The mean mIoU on the validation scenes was 0.93 with masks from the dataset annotations and 0.65 with YOLO masks, and on the ScanNet++ test scenes it was 0.80 and 0.54. Compared with thresholding the evidence per view, as a previous version of the method did, the fraction improves the test mIoU by 0.24 and makes it possible to use a single threshold for all the classes and scenes of both datasets. Finally, the error analysis shows that most of the remaining error comes from the detector. --- ### Neural Petri flows for chemical reactions Authors: Jose Eduardo Escrig Molina, Daniel Probst Published: 2026-10-06 Categories: cs.LG, physics.chem-ph, q-bio.QM arXiv: https://arxiv.org/abs/2610.08750v1 Petri nets have been used to describe chemical processes such as reactions.They map well to chemistry: Places are the bonds between atoms and the free valence of each atom, a token is a unit of bond order, a transition forms or breaks a bond, the conserved quantities are the valence budgets of the atoms, and the enabling rule is the valence rule. These semantics are not guaranteed by learned models of reactions or neural networks that are built on Petri nets that use the net as a scaffold for message passing. Here, we ask what architecture remains a Petri net for every value of its weights. We find the answer in the theory, where all semantics of a net share the firing form $m^\prime=m+Cσ$, locality, as enabling reads only the inputs of a transition, and the enabling rule, and we prove that conservation forces the firing form and that non-negativity forces the enabling rule on local rate laws. This leaves free the rate law, which is the propensity of each transition to fire. We introduce Neural Petri Flow, which learns this rate law, or a readout for classification, and hard-wires the rest as parameter-free layers. On what we denote a valence net, atom mapping, reaction classification, and forward prediction become three tasks on one firing vector. Without training, the minimum firing vector maps 88.8% of the curated Golden set against 85.6% for RXNMapper, and 88.7 against 77.9% of the enzymatic reactions of EnzymeMap. On USPTO-480K, NPF trained on these firing vectors predicts 87.7% of the products and 67.4% when trained on a 1% subset of the training reactions. EC numbers of ECREACT are predicted at the third level for 90.2% of reactions, 5.6 points ahead of the best published method. With electrons as tokens, the same token game predicts 90.5% of the elementary steps of FlowER first, ahead of the published baseline, and every top-1 prediction is a valid molecule without a filter. --- ### The Missing Minimal Pair: Stereotype Evaluation in LLMs Authors: Nataliya Stepanova, Ivan Titov, Emily Allaway, Björn Ross Published: 2026-10-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.08747v1 A common approach to measuring bias in Large Language Models is to compare the log-likelihoods of two contrastive stereotype sentences. We argue that such single-pair comparisons are often unreliable: simply rewriting the same stereotype with an alternative attribute can yield logically inconsistent preferences. To address this, we propose a dual minimal pair setup that introduces two axes of comparison for robust stereotype evaluation. First, we present a data-augmentation framework that fills critical gaps in existing stereotype datasets by generating paraphrases and alternate attributes. We apply our framework on a set of English, Russian, Spanish and Chinese stereotypes. Second, we introduce two evaluation metrics tailored to the dual minimal pair setup. One of these metrics provides a new perspective on bias by modeling the mutual information (MI) between social groups and stereotyped attributes. This MI-based metric is better suited for aggregation and enables more robust comparisons of stereotype strength across different languages and models. Our code is available at https://github.com/stepanat/missing-minimal-pair/. --- ### Linear Bandits under Exact Sliding-Window Constraints Authors: Seyed Mohammad Hadi Hosseini, Yasin Abbasi-Yadkori, Sattar Vakili Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.08745v1 We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the reward function is known, we show that convexity and cyclic-shift invariance make a stationary solution optimal when $w\mid T$ and within an additive $O(w)$ gap otherwise. In the online setting, we show that geometric structure alone is insufficient for learning, and sublinear regret can be impossible. We introduce a transition diameter $τ$ that quantifies feasible reachability and develop a rare-switching OFUL algorithm with regret $\widetilde{O}(d\sqrt{T}+τd+w)$ against the offline-optimal feasible trajectory. Finally, we remove cyclic invariance and consider general sliding-window constraints, where optimal behavior may be non-stationary. We represent recent action history as the state of a finite-memory control problem and introduce a history-state diameter $D$ that measures feasible communication between viable histories. Combining optimistic remaining-horizon planning with rare policy updates, we obtain a regret bound of $\widetilde{O}(d\sqrt{T}+dD+w)$. We evaluate our approach on real-world and synthetic benchmarks, showing that it maintains exact feasibility while achieving reward and regret comparable to baselines with substantially fewer policy updates. --- ### Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation Authors: Wenwen Si, Honghao Wei Published: 2026-10-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.08743v1 Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within a session. We propose Reinforcement Learning with Calibrated Pruning (RLCP), which adapts the retained action set using critic scores and an online threshold. The threshold is updated from binary feedback indicating whether the set contains an action in a proxy target. We prove a deterministic bound on the observed proxy miss rate along adaptive trajectories. To quantify the effect of pruning on reward, we derive an exact decomposition of value loss into filtering and selection losses. Under explicit proxy and critic approximation conditions, this decomposition yields a finite session reward bound that also accounts for imperfect selection and set truncation, without requiring the learning parameters to converge. Experiments on KuaiRand-Pure and MovieLens 1M compare two RLCP implementations with four RL baselines. In each of the 19 configurations, at least one RLCP variant achieves the highest catalog diversity, reaching $1.11\times$ to $5.21\times$ that of the strongest baseline, with competitive session depth and no larger retained sets. --- ### On the Computational Tractability of Robust Bandits Authors: Vanessa Kosoy, Vinayak Pathak Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.08740v1 Learning when the environment does not belong to the learner's hypothesis class is typically handled using agnostic learning guarantees. However, for anything beyond supervised learning, agnostic guarantees are difficult to come by. Recently, imprecise bandits (Kosoy, 2025) (later renamed to robust bandits in Appel and Kosoy, 2025) were introduced as another approach to unrealizable learning in the bandits setting and a $Θ(\sqrt{T})$ regret learner was shown for a large class. However, no computational guarantees were provided. In this paper we identify a special case that admits a polynomial-time learner with $\tilde{O}(\sqrt{T})$ regret. We also show that several small generalizations of this special case are NP-hard thus indicating that the special case is at the boundary of what is tractable. It has been recently suggested (Kosoy, 2018) that computationally efficient learners for unrealizable learning problems are crucial for solving the AI alignment problem. This work is a small step in that direction. --- ### Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling Authors: Mathias Ollu, Nikos Komodakis Published: 2026-10-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.08738v1 Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recently, continuous diffusion and flow matching models have seen substantial gains, driven by carefully crafted token representations and diffusion/flow spaces. In this work, we introduce Hierarchical Continuous Diffusion Language Models (H-CDLMs), a simple framework that further improves continuous DLMs with minimal compute and parameter overhead. Drawing on the discrete DLM and continuous image diffusion literature on joint diffusion, we diffuse multiple modalities in parallel. These modalities represent tokens at different semantic granularities: in our instantiation, the tokens themselves and coarser clusters obtained by clustering pretrained token embeddings. We propose a general setup that allows per-modality samplers and schedules to enhance the interplay between modalities. Applied to CoBit, this yields H-CoBit, which delivers large empirical gains across benchmarks. At dataset entropy, H-CoBit improves MAUVE and reaches a generative perplexity (GenPPL) of 49.4 on LM1B and 50.4 on OWT, improving on the baseline by 24.2 and 20.7 points and surpassing even discrete DLMs of comparable size. On GSM8K, it reaches 27.4% accuracy, outperforming prior continuous diffusion and flow-based models. We further apply H-CDLM to the flow matching model FLM, obtaining consistent gains with H-FLM and demonstrating that the framework generalizes across continuous generative paradigms. Our code will be made publicly available at https://github.com/matol-16/HCDLM.git . --- ### Optimal and Efficient Online Inverse Optimization Authors: Anupam Gupta, Guru Guruganesh, Honghao Lin, Vahab Mirrokni, Renato Paes Leme, David P. Woodruff Published: 2026-10-06 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2610.08735v1 In online inverse linear optimization, a learner recommends an action and then observes the choice of an expert who maximizes a fixed, unknown linear objective on $\mathbb{R}^{d}$; the goal is to learn to optimize this objective without observing it. Sakaue recently obtained the optimal regret $O(\sqrt d)$ with a randomized algorithm making $(dT)^{O(d)}$ linear optimizations per round, and asked whether it can be attained in polynomial time. We answer positively: our deterministic algorithm has regret $O(\sqrt d)$ for every horizon $T$ and runs in time polynomial in $d$ and $T$. It is a variant of the variable-metric algorithms of Sakaue et al.\ and Cai et al., in which a metric update is revoked once the query point moves far enough from where the update was made. --- ### A Systematic Study of Semantic ID Spaces for Generative Information Retrieval Authors: Alexia Allal, Hicham Randrianarivo, Sylvain Lamprier Published: 2026-10-06 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2610.08732v1 Generative Information Retrieval (GIR) has emerged as a transformative paradigm, shifting document retrieval from a traditional "retrieve-and-rank" workflow to sequence-to-sequence generation, where a model directly predicts document identifiers (DocIDs). While the semantic design of these DocIDs is known to be critical for performance, a fundamental question remains under-explored: what makes a good DocID? Current approaches rely heavily on computationally expensive downstream evaluations, hindering systematic analysis and rapid iteration. In this work, we address this challenge by presenting a comprehensive study on the properties, metrics, and trade-offs that define effective numerical DocIDs. Specifically, our contributions are threefold: First, we propose a unified framework that unifies Product Quantization (PQ) and Residual Quantization (RQ), and their hybrid variants within a single design space. This enables us to systematically study key DocID properties, such as hierarchy versus parallelism, as well as the impact of hyperparameters like DocID length and codebook size. Second, we define a suite of training-free, intrinsic metrics, to quantify DocID quality and evaluate structural fidelity without the overhead of full model training. Through extensive experiments on MS MARCO 300K and NQ320K, we analyze how these structural properties influence retrieval effectiveness. --- ### EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning Authors: Lihan Zha, Shresth Grover, Tenny Yin, Samuel M. Bateman, Hengkai Pan, Mengchao Zhang, Aykut Onol, Allen Z. Ren, Dhruv Shah, Anirudha Majumdar Published: 2026-10-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.08726v1 Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory target for control. Our key insight is that, although low-level actions are embodiment-specific, their underlying motion intent can capture task-relevant structure that transfers across humans and robots. We introduce EgoLAP, a VLA pre-training framework that jointly learns from human and robot trajectories through a shared language-based action chain-of-thought. EgoLAP expresses motion intent as structured, temporally abstracted language actions and pairs them with motion-level reasoning grounded in scene geometry, physics, and object affordances. Across extensive real-world and simulated experiments, EgoLAP transfers human experience to robot control more effectively than alternative action representations and reaches 80.1% mean real-world task progress, a 2.3x performance gain over alternative action representations. Motion-level reasoning also outperforms a composite reasoning format that combines subtask, object-box, and visual-trace reasoning. --- ### Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus Authors: Egor Pakhomov, Erik Nijkamp Published: 2026-10-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.08722v1 Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts when a compaction will hurt. TRACE's public corpus of 590 harness-triggered AppWorld compaction boundaries replays each boundary from a re-executed prefix state under the pre-compaction context and under the summary, and records the burden of the next actions: calls that error or repeat a call already made. We find that pre-boundary history predicts post-compaction harm only weakly. An internally prespecified contrast by prefix placement is a wide null, and the naive "has-written" label behind it turns out to measure trajectory phase. The best extension-protocol trigger reaches held-out AUROC 0.66 (0.64 on the replicate's own label) against a same-boundary replicate of 0.72; the best frozen, interpretable trigger avoids 21% of harmful (positive-burden) boundaries while keeping 84% of compaction opportunities, and exceeds the random-rule expectation on count but not on burden mass (a post hoc comparison). Whether the best trigger beats a token-budget rule at matched retention cannot be evaluated on the release. We state what corpora should ship to answer it. --- ### WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation? Authors: Siru Jiang, Yongzhe Lyu, Shuo Lu, Yubin Wang, Yuxiang Zhang, Yue Liao, Bin Wang, Jian Liang, Tieniu Tan Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.08720v1 LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films. As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time. Building such solvers requires physical understanding to identify appropriate models, mathematical reasoning to formulate the underlying dynamics, and software engineering to implement them as executable code, yet this capability of LLM agents remains underexplored. To this end, we introduce WorldSolver, a benchmark of 168 simulation tasks derived from physical phenomena in 61 classic computer graphics papers, spanning 7 physical domains. Each task contains a code scaffold that provides a fixed simulation environment for the scene, with the solver implementation left for the agent to complete. Specifically, we evaluate them along three dimensions: Execution Checks for successful execution, Visual Fidelity for reproducing the intended dynamic behavior in the rendered simulation, and Physical Plausibility for physics-grounded verification of the generated dynamics. Experiments on frontier agents reveal that producing executable solvers is difficult itself, and satisfying visual and physical correctness is even harder. GPT-5.6-Sol and Claude-Opus-5 perform comparatively better than the other evaluated agents, yet achieve overall scores of only 48.7% and 46.7%, respectively. WorldSolver is an early step toward agentic solver generation, and we hope it helps drive progress toward agents that can faithfully simulate the dynamic physical world. Code is available at https://github.com/sirujiang/WorldSolver. --- ### Holdout Best-of-N: Unbiased Evaluation and Its Cost Authors: Shrey Shah, Yinheng Li Published: 2026-10-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.08719v1 Reusing the scores that select a Best-of-$N$ winner can overstate its expected reward. We study evaluation from a fixed matrix of $K$ independent scores per candidate for a policy that selects using $J$ fresh scores. A single estimator based only on this matrix is exactly unbiased for expected judge reward under every independent, stable collection of candidate-specific score laws if and only if $J<K$, for every pool size $M\ge N\ge2$. At $J=K-1$, the selector deepens as $K$ grows. For independent Gaussian scores with common variance and fixed $M\ge N\ge2$, the unbiased minimax risk in this regime is of order $σ^2/\sqrt K$, attained by Holdout; allowing bias improves the rate to $σ^2/K$. For two candidates, we derive the minimum-variance unbiased estimator at known variance and the sharp asymptotic unbiased minimax constant $1/(π\sqrt2)$, which Holdout attains without knowing the variance. The cyclic average over subsets and ties can be computed in $O(MK\log M)$ operations. At fixed selector depth, cyclic evaluation of bounded scores has $O(K^{-1})$ risk uniformly in pool size. The impossibility result concerns the fixed matrix: one additional fresh winner score permits unbiased evaluation of the all-$K$ policy. --- ### When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting Authors: Vedant Palit, Florent Draye, Nicolas Zucchet, Zhijing Jin, Bernhard Schölkopf Published: 2026-10-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.08718v1 Knowledge that a language model appears to forget during finetuning often remains stored and can be recovered, a phenomenon called spurious forgetting. Finetuning on new facts can even produce forgetting that undoes itself: recall of the old facts collapses, recovers as training continues on new facts alone, and only then erodes for good. We seek to understand when such forgetting is not catastrophic. A minimal associative memory reproduces these dynamics with three ingredients: keys with shared structure, concentrated new values, and normalization in the network. Finetuning moves all old representations along a common direction, hiding the old facts while preserving their relative geometry; normalization withdraws this shift once the new facts are learned, whereas fact-specific changes accumulate and cause the erosion. Moreover, subtracting the common shift eliminates the collapse in a Transformer trained on synthetic data, and removing a single direction from each weight update restores old facts in a pretrained language model. Forgetting thus combines a shared, reversible loss of access with a slow erosion of individual facts, and only the second is catastrophic. Which one dominates depends on whether the new data move old memories together or apart. --- ### Co-Evolving Paths and Flows via Path-Flow Alignment Authors: Zeyu Michael Li, William Xingxu Chen, Xiang Cheng Published: 2026-10-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.08717v1 We study path-flow alignment as a unified training objective for flow matching. Instead of fixing the interpolation path and learning only the velocity field, we jointly train an endpoint-preserving path network and a flow network using the same alignment loss: the flow learns to match the path velocity, and the path learns to align its velocity to the current flow. Although every fixed learned path defines a valid flow-matching objective, the alignment loss alone is not a reliable criterion for path learning. We identify path overfitting, a failure mode in which the alignment loss decreases while sample quality worsens. We find that this failure is associated with low-entropy bottlenecks in the induced probability path, where the learned path routes samples through overly concentrated intermediate marginals. Motivated by this diagnosis, we introduce a stochastic path regularizer that hides part of the source information from the path network while preserving exact endpoints. The resulting regularization gives an explicit entropy floor for the stochastic training-path marginals and empirically suppresses the bottleneck in the learned sampler, making joint path-flow training effective. On ImageNet-256x256 with SiT backbones, our method consistently improves FID across model scales, extends to model-guidance training, and leaves the inference-time architecture and sampler unchanged. Code is available at https://github.com/lizeyu090312/traj_opt_paper --- ### Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval Authors: Hicham Randrianarivo, Logan Renaud, Alexia Allal Published: 2026-10-06 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2610.08716v1 Generative retrieval trains a language model to generate the identifier of a relevant document. Recent work replaces the autoregressive decoder with diffusion, but changes identifiers, training recipe and decoding at once, so differences cannot be credited to the paradigm. On NQ320K and MS300K, we train autoregressive, masked-diffusion and block-diffusion models with residual-quantised, product-quantised and random identifiers. With identifier length and training budget fixed, we decode each model in several ways. Decoding alone moves a diffusion model's Hit@1 by 6.6 to 13.7 points. Our reference diffusion decoding, generate-and-match, generates an identifier, then retrieves the closest corpus identifiers. The generated identifier is right for 14-21% of NQ320K queries. We test one-pass scoring to decode diffusion retrievers: the model reads a fully masked identifier once, and each document is scored by its codes' probabilities. It matches or beats generate-and-match in 11 of 12 settings. Autoregressive models still lead in Hit@1; on NQ320K, the lead comes from the model, not beam search. Starting from one sampled identifier, one-pass scoring removes 46-83% of masked diffusion's deficit to beam search; from generate-and-match, at most a quarter. On NQ320K, every paradigm largely memorises which identifier answers which query: random identifiers keep 83-90% of the Hit@1 of residual-quantised ones. There, product-quantised identifiers lead residual-quantised ones by 3.4 points in the autoregressive model and by -0.7 to +3.6 in diffusion models; across decodings, AR's gap exceeds diffusion's by 1.5-2.3 points, around our 2-point threshold. Paradigm comparisons must report each paradigm at its own recipe and best decoding. --- ### Prediction-powered inference for time series across space Authors: Shahzar Rizvi, David Burt, Vishwak Srinivasan, Renato Berlinghieri, Stefano Del Col, Tamara Broderick Published: 2026-10-06 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.08715v1 The following motif is common in spatiotemporal settings: we have a sequence of covariate and label pairs observed for a relatively short, recent time period. We have access to unlabeled covariates over a longer time period. Data is observed over many spatial locations. For instance, crop yield might be observed over a large geographical area for recent years, but weather data (which is informative about crop yield) is available for a much longer period. The goal is to estimate, at each spatial location, the expected label (e.g., crop yield) in the future and provide a valid confidence interval for this value. The observed time period alone is too short for reliable estimates. Imputing missing labels with machine learning can cause substantial bias. Prediction-powered inference (PPI) can correct for this bias, but it relies on an i.i.d. assumption that breaks under our expected temporal dependencies. Heteroskedasticity and autocorrelation consistent (HAC) procedures account for temporal correlation, but have not been adapted to cases where some labels are imputed. We provide reliable point estimates and confidence intervals given: short labeled time series (across spatial locations), a longer unlabeled time series, and an imperfect predictor of labels given covariates. We show our method outperforms natural alternatives. --- ### SpaTime: Streaming Vision-Language Models for Spatio-temporal Reasoning Authors: Hairong Yin, Huangying Zhan, Shin-Fang Chng, Yi Xu, Raymond A. Yeh Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08713v1 Embodied agents must reason about 3D space while the video is still arriving, answering questions as soon as they have observed enough of the scene. VLMs that incorporate 3D geometric priors achieve strong spatial reasoning, but they operate offline, i.e., the full video must be available before they produce an answer. Streaming VLMs process frames causally and decide for themselves when to respond, yet they lack explicit 3D representations. We present SpaTime, a streaming VLM that fuses causal geometry tokens into the language model at every frame, using only the frames observed so far. To supervise when the model answers, we propose a response-time loss that maps per-frame response probabilities to a differentiable expected response time and penalizes the distance from the ground-truth frame. For evaluation, we construct StreamVSTI-Bench and StreamVSI-Bench, streaming adaptations of VSTI-Bench and VSI-Bench. On StreamVSTI-Bench, SpaTime reaches 49.2% overall accuracy and reduces the mean response-time error by 66% relative to the strongest streaming baseline. --- ### Local Content-Style Control for Diffusion-based Image Stylization Authors: Amir Semmo Published: 2026-10-06 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2610.08704v1 Image stylization with latent-diffusion models entangles two independently refined axes: what a region depicts and how it is depicted. Such pipelines expose only global controls, yet professional retouching demands deliberate, region-specific control. We lift two conditioning weights already present in a ControlNet + IP-Adapter stylization pipeline from global scalars to per-location spatial maps, yielding local, per-axis control of content and style in a single generative pass. Because the two weights act on disjoint pathways, adjusting them independently spans a 2x2 retouching vocabulary, from free regeneration to identity preservation. We validate that edits stay confined to the retouched region and that each weight predominantly steers its own axis. Our approach requires no retraining and drops unchanged into any such pipeline. --- ### Agreement Is Not Validity: Cross-Model LLM Consensus in Diagnosing Student Failure Modes in K-12 Math Tutoring Dialogue Authors: Clayton Cohn, Joyce Fonteles, Kirk Vanacore, Gianni Mazza, Candida Crawford, Tom Hooper, Gautam Biswas, Rene Kizilcec Published: 2026-10-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.08703v1 In K-12 mathematics tutoring, student-tutor dialogue provides rich evidence of learners' problem-solving processes and sources of difficulty. Learning analytics research increasingly relies on large language models (LLMs) to extract such information from dialogue for a variety of downstream tasks, including knowledge tracing, behavioral modeling, and diagnosis of student reasoning errors. However, the validity of these model-generated interpretations remains insufficiently understood. In this exploratory study, we examine the validity of LLM classifications of five student failure modes in mathematics tutoring dialogue using an operational diagnostic codebook: uncertainty, misattribution, operator selection, conceptual gap, and procedural slip. Across models, human-LLM agreement was moderate (kappa = .524-.597), while cross-model agreement was substantially higher (kappa = .755-.781; alpha = .769). These findings show that cross-model agreement can create a misleading appearance of correctness, challenging the assumption that consensus among LLMs constitutes evidence of valid learner interpretation. For learning analytics, the implication is clear: scalable labeling is useful only if the inferred constructs are valid, and model consensus cannot substitute for independent evidence of that validity. --- ### nanoMuse: An Open-Source Personal Agent for Every Device You Own Authors: Guangyi Liu, Yong Liu, Jiangning Zhang Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.08699v1 Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country. Such an agent is expected to act on a person's accounts and devices, remember them across weeks, speak first when it is worth it, and answer for what it did. It is a kind of software, not a model, and until now had no open counterpart. This report defines the personal agent in five questions and three horizons. It reads how Muse is built from Meta's public record and a copy of its production prompt, each statement marked by its source. It then presents nanoMuse, the open-source counterpart under the GPL-3.0, one agent on every device a person owns, with hands on the phone's screen and the computer's. They share one conversation over a relay anyone can run; every action goes through a Sentinel, memory is files the person can read, and the model is their choice. Its size and cost are given as estimates. What is open, memory with provenance, an evaluation suite for the hands and an open model for them, is set out as a roadmap. --- ### GeneICL: A Tabular Foundation Model for Bulk Transcriptomics Authors: Michael Bohl, Alexander Theus, David Wissel, Valentina Boeva Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.08694v1 Gene expression is widely measured in biomedicine, yet clinical outcome prediction remains challenging due to high dimensionality, strong feature correlations, and limited labeled data. Large self-supervised transcriptomic foundation models often fail to outperform simple supervised baselines. Tabular foundation models offer an alternative through in-context learning, but are typically pretrained on generic synthetic data rather than transcriptomic structure. We ask whether transcriptomics-aware pretraining, rather than scale, is the missing ingredient. Towards this end, we introduce GeneICL, a 4.2M-parameter tabular foundation model combining a semi-synthetic pretraining prior built from measured bulk expression profiles with a parameter-efficient recurrent architecture. We further enable right-censored survival prediction via a training-free reduction to regression using Cox partial-likelihood residuals. We evaluate GeneICL on 80 clinical outcome-prediction tasks spanning classification, regression, and survival. Tabular foundation models consistently outperform self-supervised transcriptomic models, while GeneICL achieves the best overall rank among evaluated foundation models and tuned baselines. GeneICL does so with up to 387$\times$ fewer parameters, no gradient updates at inference, and predictions within seconds on a laptop CPU. --- ### ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences Authors: Mingda Zhang, Wenjin Liu, Tiesunlong Shen, Zikai Xiao, Zhenghong Lin, Qing Xu, Erik Cambria, Xiaoying Tang, Haoran Luo Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.08691v1 Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do not examine this process across sequential tasks in both the natural and social sciences. We formalize ScienceClaw as fixed-parameter program self-evolution that unifies task solving, scientific verification, and program updates. ScienceClaw-Eval spans 23 disciplines and measures scientific correctness, evolutionary gain, retention, cross-dataset transfer, and evolution cost through sequential streams and independent reset evaluation. Our framework repairs executable workflows through multi-turn interaction, converts re-execution-verified failure--success trajectories into linked Skill and Operator candidates, and retains an update only when source-task replay reproduces the repair and independent scientific tasks improve. Code is available at https://github.com/beita6969/ScienceClaw. --- ### Probabilistic Counterfactual Inference for Discrete Outcomes in Gaussian-Process Causal Models Authors: Juliette Sinnott, Amir-Hossein Karimi, Mohammad Kohandel Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.08689v1 Counterfactual inference in Gaussian-process structural causal models (GP-SCMs) has been developed primarily for continuous endogenous variables, limiting applicability to causal graphs that contain discrete child nodes with continuous parents. We introduce a unified probabilistic framework for counterfactual inference with heterogeneous variable types by pairing GP predictors with explicit exogenous noise mechanisms. For discrete outcomes, we derive exact conditional noise-abduction procedures using a uniform threshold for binary variables, a Gumbel-max race for nominal categories, and a latent Gaussian cut-point model for ordinal ones. In each case, we propagate abducted noise through interventions while accounting for posterior uncertainty in the GP latent functions, and prove that the resulting mechanisms reproduce the fitted model's observational and interventional distributions. On synthetic SCMs with known ground-truth counterfactuals, we evaluate estimation accuracy, consistency, and robustness to coupling misspecification. A key finding is that applying a categorical coupling to ordinal data inflates counterfactual error roughly threefold even when observational fit remains comparable, and that this error does not diminish with more data. As the training set grows, the fitted structural equation converges to the truth while the counterfactual error flattens onto a floor. In the reverse direction, forcing a false order onto nominal data instead degrades the fitted equation itself. The choice of coupling must therefore be justified on structural grounds rather than read off the fit. --- ### RenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital Twins Authors: Dicong Qiu, Zhiyuan Xu, Yaosheng Liu, Feng Han, Bo Ye Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08684v1 Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, and motion. Evaluating this render-to-real capability requires a real target video depicting the same scene evolution, paired with an editable, geometrically registered 3D replica. Such data has traditionally required substantial manual modeling, calibration, and animation effort. We introduce RenderBench, a benchmark of 12 reconstructed real-world scenes spanning large-scale indoor environments and egocentric viewpoints, with both static and dynamic settings. Our construction pipeline combines visual geometry, neural reconstruction, and assisted 3D authoring. Each scene is decomposed into static objects and dynamic actors, registered to the capture cameras, and accepted only after multi-view geometric and temporal validation. Each evaluation unit contains appearance reference images, a held-out real target video, an editable digital twin, a matched proxy render, and renderer-native scene annotations. We evaluate transfer models against paired real target videos, retain PAI-Bench-C-compatible structural projections, and use scene annotations to localize failures by object, visibility, articulation, and motion. The first release retains 12 of 14 registered samples (85.7%), comprising 1,496 paired real-proxy frames. All released scenes pass file-integrity and environment-edit audits, while proxy diagnostics yield a depth si-RMSE of 0.2170 and instance mIoU of 0.3673. RenderBench provides paired real observations and editable scene state for assessing both appearance fidelity and preservation of geometry and dynamics. --- ### Coupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted Dialogue Authors: Lichen Zhu, Yueqian Lin, Yiheng Wang, Hai "Helen" Li, Yiran Chen Published: 2026-10-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.08683v1 Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation. In that loop no human absorbs a timing error: each model's turn-taking is the other's input. We ask what timing the loop settles into. Two PersonaPlex-7B instances exchange audio tokens on a shared clock in unscripted conversation, and one floor-transfer rule is applied to them and to Switchboard. Their timing is coupled: re-pairing speakers across conversations destroys it. But the floor changes hands late, at a median of 400-560 ms against 137 ms for humans, and the last 120 ms of the partner's turn, where human projection places a tenth of its transfers, holds 1% of theirs. Delaying one direction of the channel shifts the response one-for-one and leaves the run-up to it empty, consistent with a reactive wait after the perceived end rather than the turn-end projection human timing requires. --- ### A Systematic Study of Small Language Models on Abstract Reasoning Tasks Authors: Nur A Zarin Nishat, Jens Lehmann, Andrei Aioanei, Sahar Vahdati Published: 2026-10-06 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.08680v1 Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-specific regularities. We study this distinction in small language models on the ARC-TGI benchmark, which organizes abstract grid transformations into controllable task families and supports resampling, spatial shifts, and cross-benchmark transfer. Across more than 1,000 runs, we profile decoder-only, encoder--decoder, and mixture-of-experts model families under supervised fine-tuning. We examine the efficiency and stability of skill acquisition, robustness beyond the training distribution, interactions with model family and task formulation, and layer-wise attention signatures that accompany behavioral differences. Substantial in-distribution accuracy is attainable, but acquisition is sensitive to optimization and unevenly distributed across task families. Performance deteriorates sharply outside the training distribution, including when the rule is retained but grid scale changes. Greater training-set depth and breadth yield uneven gains, while the effect of additional in-context examples depends on model family. Executable-rule induction also yields correct solutions not observed under direct grid generation. On selected tasks, attention diagnostics show distinct concentration and context-dependence profiles, but do not establish general causal mechanisms. Overall, abstract-reasoning scores are conditional on the model, adaptation regime, evaluation distribution, and response format. --- ### Secure Speculative Decoding for Large Language Models Authors: Yichi Zhang, Zhiqi Wang, Neil Gong, Yuchen Yang Published: 2026-10-06 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.08678v2 Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model}, to generate candidate tokens and then verifying them with the target model for acceptance or rejection. Prior studies primarily focused on the efficiency-utility trade-off of speculative decoding, e.g., lossy speculative decoding, leaving its security implications largely unexplored. In this work, we bridge this gap by providing the \emph{first} systematic study of the security implications of speculative decoding. Through a large-scale measurement study, we reveal a pronounced security-utility asymmetry: across a wide range of lossy speculative decoding methods, improvements in inference efficiency come at a disproportionately high cost to security, with attack success rates for jailbreak and prompt injection attacks increasing much faster than utility degrades. We then propose SecureSD, a new theory-guided speculative decoding method that enhances security while maintaining efficiency and utility. Specifically, our theoretical analysis reveals that security degradation primarily originates from the early tokens generated by the draft model. Motivated by this insight, SecureSD applies a stricter verification criterion to draft-model tokens at early decoding positions. Extensive experiments on both security and utility benchmarks demonstrate that SecureSD significantly improves security while preserving efficiency and utility compared to existing speculative decoding methods. --- ### Secure Speculative Decoding for Large Language Models Authors: Yichi Zhang, Zhiqi Wang, Neil Gong, Yuchen Yang Published: 2026-10-06 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.08678v1 Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model}, to generate candidate tokens and then verifying them with the target model for acceptance or rejection. Prior studies primarily focused on the efficiency-utility trade-off of speculative decoding, e.g., lossy speculative decoding, leaving its security implications largely unexplored. In this work, we bridge this gap by providing the \emph{first} systematic study of the security implications of speculative decoding. Through a large-scale measurement study, we reveal a pronounced security-utility asymmetry: across a wide range of lossy speculative decoding methods, improvements in inference efficiency come at a disproportionately high cost to security, with attack success rates for jailbreak and prompt injection attacks increasing much faster than utility degrades. We then propose SecureSD, a new theory-guided speculative decoding method that enhances security while maintaining efficiency and utility. Specifically, our theoretical analysis reveals that security degradation primarily originates from the early tokens generated by the draft model. Motivated by this insight, SecureSD applies a stricter verification criterion to draft-model tokens at early decoding positions. Extensive experiments on both security and utility benchmarks demonstrate that SecureSD significantly improves security while preserving efficiency and utility compared to existing speculative decoding methods. --- ### Variance-Optimal Off-Policy Evaluation with Conjunct Effect Modeling Authors: Nicolò Felicioni, Michael Benigni, Maurizio Ferrari Dacrema, Paolo Cremonesi Published: 2026-10-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.08677v1 Off-policy evaluation (OPE) for contextual bandit policies becomes challenging when action-level importance weighting incurs excessive variance. Doubly robust (DR) estimation remains unbiased under common support but retains these high-variance action-level weights. A prior estimator, Off-policy evaluation with Conjunct Effect Model (OffCEM), replaces them with more stable cluster-level weights, at the cost of relying on local correctness of the reward model. In this paper, we show that, under the assumptions required by DR and OffCEM, there exists an unbiased family of estimators that interpolates between OffCEM and DR. Building on this result, we propose the Variance Optimal-CEM (VOCEM) estimator, which selects the interpolation coefficient to minimize variance. We derive the population-optimal coefficient in closed form and show that the resulting estimator has variance no larger than either endpoint, OffCEM or DR. Experiments in controlled synthetic settings and on two large-action benchmarks show that VOCEM improves upon both endpoints in all 23 evaluated conditions, exhibiting greater stability and empirical robustness. --- ### Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge Authors: Chuhong Xu, Bo Su, Ziyao Chen, Ruiyang Xu, Shimeng Dai, Xinyu Qiu Published: 2026-10-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.08675v1 Financial reports repeat values across periods, metrics and accounting lines, allowing an LLM-generated calculation to be numerically correct while citing the wrong financial role. We evaluate what probabilistic evidence verification adds beyond number matching using Jev as a source-support verifier for GPT-4.1-mini calculation traces. A signed-number-at-pointer baseline explains most recovery over exact quotation checks. To isolate the remaining role-recognition problem, we hold operands and arithmetic fixed, move citations between same-number cells, and retain controls that express equivalent facts. These contrasts reveal both wrong-role citations that pass and valid alternative citations that are withheld. Explicit column labels improve selected wrong-role decisions while also lowering support for some equivalent evidence. A constructed follow-up on 36 new source pages, labeled by a non-author reviewer, extends this evaluation and exposes the same tradeoff between detecting role errors and retaining valid citations. The contribution is a controlled evaluation that identifies what a probabilistic financial verifier distinguishes when numerical matching is held fixed. For LLM-based financial assistants, it makes numerical correctness, cited-role support and acceptance outcomes separately assessable. --- ### EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding Authors: Yuhao Qin, Junbo Wang, Yuke Li, Yining Zhu Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08674v1 Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an explicit event chain before question answering. Instead of retrieving isolated frames or text segments, EC-RAG first partitions the video into semantically coherent segments, represents each segment using multi-modal signals, and then links them into a structured chain that preserves temporal order and captures inter-event relationships. Given a query, the system identifies relevant events within this chain and gathers supporting evidence from the associated modalities. Our approach offers several practical advantages: (i) event-level abstraction that better reflects how video content is naturally structured, enabling more reliable localization compared to frame-level retrieval; (ii) structured multi-modal fusion that aggregates speech, text, and visual cues at the event level, allowing complementary information to be more effectively utilized during reasoning; and (iii) plug-and-play compatibility with existing LVLM backbones, requiring no additional training or reliance on proprietary models. Experiments on Video-MME, MLVU, and LongVideoBench show that this event-centric design consistently outperforms frame-level retrieval baselines, highlighting the importance of modeling temporal structure for long-video understanding. --- ### PDB: Point-Based Deformation Blending for Facial Animation Retargeting Authors: Sihun Cha, Hyeonseung Shin, Suah Yu, Junyong Noh Published: 2026-10-06 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2610.08672v1 Mesh-agnostic facial animation retargeting transfers expressions across meshes with different structures, but preserving facial motion without surface artifacts remains challenging. To address this, we present PDB, Point-Based Deformation Blending for facial animation retargeting. PDB predicts a compact set of deformed control points from a source neutral-expression pair and blending weights from the target neutral mesh. The weights are computed once per target and reused across frames, while the control points vary with each source expression. ReLU enforces non-negative weights and permits exact zeros, followed by row-wise normalization. The target mesh is reconstructed directly by multiplying the weights and control points, without a predefined cage, precomputed coordinates, a learned per-element deformation decoder, or a global reconstruction solve. Trained only with self-retargeting reconstruction supervision, PDB supports cross-identity transfer without paired cross-identity training expressions. Experiments demonstrate accurate retargeting, fast inference, and localized support in the learned weights. Joint evaluation of expression accuracy and local surface preservation shows reduced surface artifacts relative to the evaluated dense displacement method while retaining the intended motion. Perceptual evaluations further support expression fidelity and visual quality in both self- and cross-retargeting. --- ### Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment Authors: Orion Reblitz-Richardson Published: 2026-10-06 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.08670v1 Language models increasingly act as agents. An agent that says an action is wrong and then takes it anyway is a different failure from one that does not know better, and evaluations of stated values cannot see it. We build a pre-registered panel of 248 scenarios across five kinds of pressure. Each scenario is posed twice to the same model, once as the agent choosing what to do and once in the third person asking which option is right, so the model's own judgment is the reference. Every scenario has a twin with the pressure removed, and every model gets a positive control in which its operator orders the violating action, so that a missing gap can be told apart from a blind instrument. On OLMo-3-7B-Instruct, the model takes the action it judged wrong on about one in five pressuring scenarios, more often than on the same scenarios with the pressure removed. Across four instruct models the gap depends on the post-training recipe: OLMo-3 and Meta's Llama-3.1-8B-Instruct carry it; Tulu 3 shows none on the whole panel (above about 0.01 in probability) or on its own most-pressuring scenarios; Qwen2.5-7B-Instruct shows none on the whole panel (above about 0.02) and is unresolved on its own (0.083, -0.028 to 0.195). Meta's recipe and Ai2's Tulu 3 start from the same Llama-3.1 weights, and only Meta's carries the gap. Reading a chat model outside its chat template reverses the sign of its gap with nothing at stake (-0.038 against +0.055 under the template on OLMo-3), a distortion present on two of three recipes. On both models that carry it, reasoning about the stakes before acting moves the choice back toward the model's own judgment, against a same-length non-moral task, with or without the pressure; on OLMo-3, naming the norm at stake does about a third of that. The gap is a measurable target for post-training recipes, not a fixed property of pretrained weights. --- ### MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge Authors: Mehmet Emre Akbulut, Johannes Geier, Ulf Schlichtmann Published: 2026-10-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.08669v1 On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass. This paper introduces Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around a memory-first design principle rather than a direct application of transformer-oriented LoRA. Instead of merely reducing trainable weights, we define an activation-memory-floor criterion: trainable backward computations must not depend on full-width layer inputs. The resulting adapter freezes the down-projection, trains a scale-matched up-projection, and combines eval-mode backbone normalization with activation-minimal backward rules, reducing saved state to the low-rank branch. Evaluated on three Human Activity Recognition (HAR) datasets and two CNN backbones under subject, body-location, and sensor-placement shifts, MemFLoRA reduces saved-activation memory by 98.5-98.7% and peak training-state memory by 94.9-97.3% relative to full fine-tuning, while matching or exceeding CNN PEFT baselines. --- ### Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents Authors: Suxin Ji, Hungtao Wan, Shaoxuan Chen, An Zhang Published: 2026-10-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.08668v1 Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when the observation is untouched; in AgentMark's own robustness test, paraphrasing the observation alone drops bit-recovery to 16.8%. Second, every prior agent watermark studies only removal: none asks whether an adversary can forge a trajectory that verifies as someone else's, a question answered affirmatively for text watermarks (Jovanović et al., 2024). We present Semantic Behavioral Watermarking (SBW): watermarking over semantic action clusters under history conditioning, with the public-cluster bin replaced by keyed collision-resistant binning whose fresh-bucket assignment is provably unpredictable in the random-oracle model. Across five agent models (3B-14B, four vendors) and three encoders the ordering holds on both benchmarks: on ToolBench (600 trajectories per model) detection under rewriting is 0.49-0.66 for cluster-level versus 0.05-0.17 for exact-symbol at a permutation-calibrated 1% FPR, at 72-83% choice agreement against 22-27% for logit biasing; on ALFWorld (100 episodes per model) it is 0.92-0.97 versus 0.00-0.01. Keyed binning takes adaptive forgery from 100% to the false-positive floor at the primary operating point (bge, r=64). We also mark the boundary that guarantee does not cover: when the adversary copies the victim's own steps, shuffled splicing is neutralized (0.000 on Qwen2.5-3B) but chained replay remains at 0.76-0.98 across the five models, reported as open. Paraphrase robustness costs about half of the per-step watermark capacity. Code is available at https://anonymous.4open.science/r/SBW-Agent-Watermark. --- ### Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction Authors: Lichen Zhu, Yueqian Lin, Yiheng Wang, Hai "Helen" Li, Yiran Chen Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08663v1 Video gaze prediction is led by gaze-trained models, yet gaze-free priors carry signal those models have not absorbed, if one knows when to trust them. We propose FocusGate, a gated ensemble of gaze-free priors whose members may abstain. A per-frame gate reads three shape statistics of a defocus map and selects the frames on which the estimator is above chance on average, so rejected frames reduce to the base exactly, while midrank normalisation lets an all-zero prior abstain at zero parameters. Gated fusion is significantly positive on film, sports and web video, whereas unconditional fusion is harmful on sports and null on web. Added to four supervised predictors, the NTIRE 2026 champion among them, FocusGate improves all sixteen model-domain cells in shuffled AUC, fifteen significantly, one domain pre-registered and scored once, while adding only 1% to the champion's latency. Alone, it surpasses TASED-Net and UNISAL in shuffled AUC on film with a 16-frame causal mean. --- ### ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding Authors: Hanjun Luo, Xiucheng Zhang, Zhuoning Xu, Zhimu Huang, Yingbin Jin, Xinfeng Li, Hanan Salam Published: 2026-10-06 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.08662v3 As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent behaviors from separate perspectives, but lacks a systematic framework for unifying these behaviors. To bridge this gap, we introduce ParanoiaEval, the first benchmark for unified evaluation of risk-treatment capabilities in coding agents. Grounded in the well-established Avoidance-Transfer-Mitigation-Acceptance framework in software engineering risk management, ParanoiaEval operationalizes its 4 fundamental treatments for coding-agent settings and contains 200 evidence-controlled repository-level task pairs, each differing only in treatment-defining evidence. We further introduce dedicated metrics for risk-treatment violations and evidence responsiveness, using a human-calibrated agentic judge for reliable evaluation. Large-scale experiments on 8 representative models and a post-hoc human study reveal that (I) unnecessary risk treatment occurs in 11.2%-58.7% of runs despite explicit evidence, with substantial variation across agent configurations; (II) stronger task capability does not ensure more appropriate risk treatment, while treatment violations substantially harm developers' experience, establishing risk treatment as an independent capability dimension; and (III) agents exhibit systematic patterns consistent with established risk-management findings, suggesting that knowledge from human practice can guide the diagnosis and improvement of this capability. --- ### ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding Authors: Hanjun Luo, Xiucheng Zhang, Zhuoning Xu, Zhimu Huang, Yingbin Jin, Xinfeng Li, Hanan Salam Published: 2026-10-06 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.08662v1 As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent behaviors from separate perspectives, but lacks a systematic framework for unifying these behaviors. To bridge this gap, we introduce ParanoiaEval, the first benchmark for unified evaluation of risk-treatment capabilities in coding agents. Grounded in the well-established Avoidance-Transfer-Mitigation-Acceptance framework in software engineering risk management, ParanoiaEval operationalizes its 4 fundamental treatments for coding-agent settings and contains 200 evidence-controlled repository-level task pairs, each differing only in treatment-defining evidence. We further introduce dedicated metrics for risk-treatment violations and evidence responsiveness, using a human-calibrated agentic judge for reliable evaluation. Large-scale experiments on 8 representative models and a post-hoc human study reveal that (I) unnecessary risk treatment occurs in 11.2%-58.7% of runs despite explicit evidence, with substantial variation across agent configurations; (II) stronger task capability does not ensure more appropriate risk treatment, while treatment violations substantially harm developers' experience, establishing risk treatment as an independent capability dimension; and (III) agents exhibit systematic patterns consistent with established risk-management findings, suggesting that knowledge from human practice can guide the diagnosis and improvement of this capability. --- ### Evidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma Radiogenomics Authors: Mariya Miteva, Maria Nisheva-Pavlova Published: 2026-10-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.08660v1 Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific evidence. We developed a neuro-semantic verification framework that converts radiomic measurements into addressable evidence records and machine-checkable claims. Methods: UPenn-GBM radiomics were aligned with de novo CaPTk extraction from standardized MRI and expert-validated segmentations in an independent multicenter cohort. The shared space comprised 1,728 features from T1, T1GD, T2, and FLAIR MRI across three tumor regions. Reference-defined semantic states were derived from 611 UPenn cases. We evaluated cross-cohort transportability, model-linked provenance, deterministic verification, controlled predictive degradation, and an LLM claim-extraction pilot; MGMT prediction served only as a transport stress test. Results: Median semantic-state agreement was 0.786 (weighted kappa 0.709), ranging from 0.918 for morphologic to 0.252 for intensity features. The external evidence ledger contained 1,655 model-linked records for 331 patients. The verifier achieved 100% exact-set accuracy in a 6,620-claim corruption benchmark. In a 24-case pilot, GPT-5.6 Sol reproduced 72/72 prespecified atomic claims, and the frozen verifier recovered 24/24 expected conditions. During controlled degradation, ROC AUC declined from 0.899 to 0.500 while verification accuracy remained 1.000. External MGMT discrimination was weak (ROC AUC 0.543). Conclusions: Verifiability can be engineered and evaluated independently of predictive performance. LLMs may structure explanations, while final evidence-consistency checking remains deterministic. --- ### Selective Transfer of RL Updates for Visual Reasoning Authors: Suxin Ji, Hungtao Wan, Mingjun Liu, An Zhang Published: 2026-10-06 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.08659v1 Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-based transfer can conflate pre-existing model differences with changes acquired during reasoning post-training. We instead formulate capability transfer around the training-stage update, isolating the parameter changes induced by reinforcement learning (RL). Yet transferring this update in full remains suboptimal: we find that its components differ substantially in cross-model transferability, with dominant directions transferring more effectively than the complete update. Based on this finding, we introduce Selective-RL, which isolates the RL-stage update, retains its dominant matrix-wise directions with magnitude preservation, and transfers them to the language modules of a VLM. Across three model families and five visual-reasoning benchmarks, Selective-RL improves full-update interpolation in 12 of 15 comparisons, including an 8.55 percentage-point MathVision gain on the Qwen recipient. Matched controls show that update magnitude or arbitrary low rank alone does not reproduce these gains. These results highlight a distinction between what is acquired during post-training and what remains transferable across models, providing a training-stage perspective on cross-model capability transfer. Code is available at https://anonymous.4open.science/r/selective-rl. --- ### Steering Diffusion Models to Rare Events with Sequential Monte Carlo Authors: Aavash Subedi, Tim Reichelt, Christopher Williams, Philip Stier, Yee Whye Teh, Saifuddin Syed Published: 2026-10-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.08652v2 Diffusion models are increasingly used as surrogates for expensive simulators in weather prediction, molecular dynamics, and materials design. In these models, computing the probability $p_0(E)$ of an event $E$ is difficult, especially when the event of interest is rare. A stable estimate using Monte Carlo becomes computationally intractable, requiring a growing sample size $\propto\!1/p_0(E)$ to compensate for an increasing rarity. In this paper, we present Diffusion rare event sampling with Sequential Monte Carlo (DireSMC), a sequential Monte Carlo scheme that guides a population of weighted samples towards the rare event, giving access not only to samples but also to a calibrated estimate of its probability. We set up our guidance using an analytical relaxation of the event set, allowing the method to easily extend to a wide range of user-defined rare events. We validate our method on a toy problem with analytical solutions and on a score-based climate emulator, where we obtain accurate rare-event probabilities on a range of rarities from $10^{-3}$ to $10^{-5}$, achieving net speed-ups of $9\times$ to $1413\times$ over Monte Carlo. --- ### Steering Diffusion Models to Rare Events with Sequential Monte Carlo Authors: Aavash Subedi, Tim Reichelt, Christopher Williams, Philip Stier, Yee Whye Teh, Saifuddin Syed Published: 2026-10-06 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.08652v1 Diffusion models are increasingly used as surrogates for expensive simulators in weather prediction, molecular dynamics, and materials design. In these models, computing the probability $p_0(E)$ of an event $E$ is difficult, especially when the event of interest is rare. A stable estimate using Monte Carlo becomes computationally intractable, requiring a growing sample size $\propto\!1/p_0(E)$ to compensate for an increasing rarity. In this paper, we present Diffusion Importance Sampling of Rare Events or DireSMC, a sequential Monte Carlo scheme that guides a population of weighted samples towards the rare event, giving access not only to samples but also to a calibrated estimate of its probability. We set up our guidance using an analytical relaxation of the event set, allowing the method to easily extend to a wide range of user-defined rare events. We validate our method on a toy problem with analytical solutions and on a score-based climate emulator, where we obtain accurate rare-event probabilities on a range of rarities from $10^{-3}$ to $10^{-5}$, achieving net speed-ups of $9\times$ to $1413\times$ over Monte Carlo. --- ### A Case Study in Assuring AI-Written Software Authors: Lindsey Ferris, Sierra Bonilla Published: 2026-10-06 Categories: cs.SE, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.08651v1 Software-engineering agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously can produce more code than even experts can meaningfully inspect. In both cases, exhaustive code review is not reliable as the sole basis for human control. We report a case study of a production healthcare platform built through coding agents and governed by an operator without formal software-engineering training. Over time, its workflow grew into a human-led meta-agent system where one agent wrote code, other agents supervised and reviewed it, and project rules carried lessons forward. The operator found that tests, monitors and reviewing agents used to supervise the system were fallible. Some monitors measured proxies rather than outcomes, some audits failed silently, missing checks disappeared from reported results and one automated repair caused operational disruption. In this case, human control depended on keeping the intended outcome, the evidence used to judge it, the agents' permissions and the final human decision were all tied to the same underlying objective. --- ### Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation Authors: Lichen Zhu, Yiheng Wang, Yueqian Lin, Hai "Helen" Li, Yiran Chen Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08649v1 Video-language models are ranked by multiple-choice accuracy on frames from a uniform grid. The grid has two parameters, a rate and a phase, and benchmarks report only the rate. The phase moves answers: two deployed samplers differing only by a half-step phase offset answer 23.6% of questions differently while scoring within a point, and across four releases from two families shifting only the phase changes roughly one answer in five after controlling option order. PHASEFUSION decodes three offset grids and averages the option posteriors. The grids are the polyphase components of the dense grid. Fusion matches a 32-frame single pass in accuracy within a prespecified margin (logit-scored) and cuts the answers a half-step shift of all three grids changes from 18.2% to 10.1%. Option order, which changes only the presentation, is flagged instead by a one-pass answer margin. Report the phase convention with the budget, or marginalize it. --- ### SquidAgent: Parallelize Wisely, Coordinate Efficiently Authors: Yexiong Lin, Shanshan Ye, Yu Yao, Zhen Fang, Bo Han, Tongliang Liu Published: 2026-10-06 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.08647v1 LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield near-linear speedups. Yet existing parallel multi-agent systems often run slower than a single-agent baseline. We attribute this gap to two hidden costs that parallel execution incurs but a serial agent avoids. First, there is a re-exploration cost: redundant effort spent by parallel workers reconstructing context that the orchestrator already possesses, such as prior decisions, that would otherwise be inherited implicitly in a serial execution. Second, there is an alignment cost: the overhead required to reconcile inconsistencies across independently generated outputs. We thus derive a principled decision criterion: a layer should be parallelized only when its critical-path cost, plus re-exploration and alignment overheads, is lower than the corresponding serial cost. While this criterion is naturally expressed in wall-clock time, we observe that LLMs are poorly calibrated when asked to estimate task duration. To address this, we instead measure cost in predicted output tokens, which we empirically find LLMs can estimate substantially more reliably than wall-clock time. Building on this token-based criterion, we propose SquidAgent. It estimates all token budgets in a single planning step, forks each worker directly from the orchestrator's session to eliminate re-exploration cost, and replaces post-hoc reconciliation with a pre-generated shared convention block that converts alignment into a bounded upfront cost. A deterministic scheduler then applies the criterion layer by layer. Empirically, SquidAgent achieves a 2.2$\times$ mean throughput improvement and a 2.6$\times$ mean wall-time speedup over Claude Code, and a 2.0$\times$ throughput improvement over the strongest multi-agent baseline. --- ### HygieneRoboBench: Benchmarking Hygiene-Aware Planning for Household Robots Authors: Yurun Chen, Josh Qixuan Sun, Jason Qin, Chengtai Li, Tianyi Wang, Mark Crowley, Wentao Zhu Published: 2026-10-06 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.08642v1 Contact with contaminated objects can spread hazards through a household robot's grippers, tools, and shared surfaces, while new contacts can make an existing plan unsafe. Existing benchmarks do not jointly assess how planners identify hygiene risks from contact history and plan safe continuations after new contact events. Planners must do so within time and resource limits while respecting user priorities. We introduce HygieneRoboBench, with 624 instances across 134 task families, to evaluate safe resolution of household tasks from a given execution history. Tasks capture contamination through two grippers and shared objects, treatment costs, and user priorities. We combine controlled history, profile, and event comparisons with independent plan evaluation. These assess safe resolution, cost efficiency under user priorities, and responses to contact events. Evaluation of LLM-based and symbolic planners shows that safely completing a task does not guarantee the lowest execution costs under the user's priorities. To address this problem, we introduce Hygiene-NSP. It combines LLM-based grounding, contact-history reconstruction, and CP-SAT to jointly plan hygiene treatment and task execution under user priorities. Hygiene-NSP achieves safe resolution and optimal safe resolution rates of 94.4% and 90.4%, respectively. Both rates are higher than those of the evaluated baseline planners on the full dataset. Project page: https://euron-zc.github.io/HygieneRoboBench/. --- ### Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection Authors: Jiahua Li, Zixu John, Tom Zhong, Fuping Wu, Tianhao Xu, Jianqing Zheng, Yuanhan Mo, Fei Shen Published: 2026-10-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.08639v1 As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existing methods primarily rely on task-specific supervision to adapt vision foundation model representations, without fully exploiting internal forensic knowledge to guide detection. To address this limitation, we propose Reserve-Guided Elicitation (RGE), a framework that treats sparse, origin-sensitive internal components in pretrained models as a forensic reserve and translates their localization into structural constraints for lightweight adaptation. Specifically, we first use the Forensic Lens (F-lens) to decompose activations across layers and token groups into independent components and globally screen them by their response differences between real and generated images, identifying reserve sites and directions. Next, we map the selected directions back to hidden-state space to construct fixed reserve subspaces and insert Forensic Reserve Adapters (FRA) only at the identified sites. Finally, with the backbone parameters, previously fitted reference classifier, and subspace bases fixed, we train only the FRA coefficient maps to generate input-dependent residual updates constrained to the corresponding subspaces, strengthening existing forensic responses. Using only 500 labeled training images and a trainable parameter budget below 0.2% of the backbone, RGE achieves competitive performance across three detection benchmarks without target-benchmark adaptation. Furthermore, RGE consistently improves over the corresponding frozen detectors across eight encoders spanning self-supervised and vision-language pretraining, eliciting a latent forensic capacity broadly shared across pretrained vision models. --- ### Spectral Recovery of Point Clouds from Noisy Geometric Graphs Authors: Tatiana Brailovskaya, Nicholas A. Cook, Sofia Poinelli Published: 2026-10-06 Categories: math.ST, math.PR, stat.ML arXiv: https://arxiv.org/abs/2610.08634v1 We study the problem of recovering low-dimensional latent geometry from a random geometric graph generated by noisy, high-dimensional data. Specifically, we analyze the performance of a spectral embedding algorithm on the Signal+Noise Graph Model, in which vertices are associated to points perturbed by Gaussian noise, and edges are included for pairs whose inner product exceeds a specified alignment threshold. In the high-dimensional regime where the number $n$ of points and the ambient dimension $d$ both tend to infinity, we show that under a spectral gap condition, the top eigenvectors and eigenvalues of the graph's adjacency matrix can be used to approximately recover the point cloud up to an orthogonal transformation. We illustrate our results on point clouds sampled from nested spheres and high-dimensional sinusoid curves. --- ### Towards In-Parameter Memory Augmentation for Large Language Models Authors: Haoyu Huang, Zhongwei Xie, Jiaxin Bai, Yisen Gao, Hong Ting Tsang, Wuganjing Song, Huihao Jing, Yufei Li, Yangqiu Song Published: 2026-10-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.08630v1 Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. \textbf{In-parameter memory} offers a complementary substrate: reusable memory information is represented in model parameters, adapters, or other parameter-like objects that are composed into the forward pass at inference time. This survey focuses on methods that augment LLMs with such parametric memory at deployment: a memory-bearing parameter object is plugged into the forward pass during inference, whether it is acquired before or during deployment. We organize the landscape with two orthogonal axes: \textbf{Parameter Placement}, which includes Embedding, Attention, FFN layers, or Hybrid when two or more layers are used; and \textbf{Parameter Acquisition Time}, which distinguishes methods whose memory object is acquired during deployment (online) from those acquired before it (offline). We clarify boundaries, conduct comparisons, and discuss open directions in interference, safety, co-design with ICL, and recursive self-improvement. ---