# Research Papers — 2026-10 · bundle page 77 of 156

> Full-text markdown of papers #3801–3850 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/77
[← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/76.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-10/page/78.md)

### Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University Building

Authors: Amey Vasulkar, Samuel Kernan Freire, Arie-Willem de Leeuw, Tadeo-Baldiri Salcedo-Rahola
Published: 2026-10-08
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2610.12638v1

Day-ahead electricity forecasts can help building operators schedule heating, ventilation, and other services around anticipated demand. Choosing a forecasting model also requires balancing accuracy with its forecast-time inputs, local training, and computational requirements. We benchmark statistical, machine-learning, recurrent neural-network, and pretrained TimesFM models for a university building. We use chronological validation and evaluate all configurations on the same 57 test days, comparing accuracy across workdays, weekends, and holidays alongside local fitting and forecasting time. Weather covariates use retrospective observations. TimesFM 3.0 with covariates achieves the lowest overall errors, reducing mean absolute error by approximately 43\% relative to weekly seasonal-naive forecasting. XGBoost remains competitive, although paired daily comparisons do not establish a clear mean-absolute-error advantage for TimesFM. TimesFM also performs strongly using only past electricity consumption. Adding covariates improves its holiday forecasts but slightly worsens workday and weekend forecasts, leaving overall mean absolute error almost unchanged. TimesFM requires no building-specific weight training, while XGBoost offers rapid local fitting and inference. The evaluated LSTM takes longer to fit without outperforming either approach. An exploratory historical evaluation reveals seasonal variation, while a separate weather-source comparison produces only small changes in the selected TimesFM configuration's accuracy. These results support pretrained TimesFM as a strong initial forecasting baseline for this building, with XGBoost as a competitive locally fitted alternative. Covariates are particularly useful when improved holiday forecasts justify the additional input preparation.

---

### ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Authors: Zekai Gu, Peng Wang, Jiahao Lu, Yongsen Mao, Cheng Lin, Yuan Liu
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12625v1

Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocate computation uniformly across space when generating the next video chunk, updating all patches with the same denoising schedule and number of function evaluations. This ignores the spatial heterogeneity of video content: static, simple, or recurring regions are often easier to denoise, while other regions require further refinement or additional context. A uniform budget thus leads to redundant computation on easy patches, whereas reducing the fixed step count can leave difficult patches insufficiently refined. We introduce \methodname{}, a general framework that dynamically allocates denoising steps to individual patches: easy patches stop early to improve efficiency, while difficult patches receive more refinement steps. This design accelerates generation with negligible quality degradation. Our method is compatible with most existing few-step autoregressive diffusion models, requiring only a lightweight routing module with modest training. Experiments demonstrate that \methodname{} reduces the total number of denoising steps applied across video patches by about 50\% while maintaining visual quality comparable to the four-step baseline.

---

### MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers

Authors: Jiuming Liu, Mengmeng Liu, Guangming Wang, Lihao Liu, Michael Ying Yang, Yunpeng Zhang, Francesco Nex, Hao Cheng, Hesheng Wang
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12624v1

Prior outdoor LiDAR registration works are commonly limited by the pair-wise input paradigm, which neglects temporal correlations inherent within streaming sequences. In this paper, we propose a novel multi-frame outdoor point cloud registration network for streaming LiDAR scans enhanced with pose-related memory buffers. The key observation is that long-term temporal LiDAR sequences can provide rich global contextual information to complete sparse measurements, filter outliers, and address low-overlap problems, thereby boosting registration performance. Specifically, two hybrid memory buffers are designed, including an implicit memory feature buffer and an explicit memory pose buffer, to store and dynamically update pose-related temporal features. Moreover, a novel dynamic history weighting module is developed to adaptively fuse current and history pose-related features. Extensive experiments on three outdoor datasets, including KITTI, nuScenes, and Apollo-Southbay, demonstrate state-of-the-art performance of MemReg, surpassing all previous pair-wise methods and also multi-frame SLAM systems. Our method also generalizes surprisingly well to multiview indoor registration scenarios with rather competitive performance on 3DMatch, 3DLoMatch, and ScanNet. Code will be released at https://github.com/IRMVLab/MemReg.

---

### Mesh-Native Tokenisation: Retrofitting Foundation Models to Unstructured Data

Authors: Georg Maierhofer, Miles Cranmer, Payel Mukhopadhyay
Published: 2026-10-08
Categories: cs.CE, cs.AI, math.NA
arXiv: https://arxiv.org/abs/2610.12618v1

Physics foundation models are an increasingly popular approach for building versatile emulators for spatiotemporal systems. They require tokenisation layers that lift physical field data into a latent representation suitable for dynamic processing. A typical choice for this layer is a convolutional encoder, which lifts field information in a locality-aware way and can be trained very efficiently. However, this choice cannot be applied to a large class of scientific computing problems where data are represented on unstructured meshes, for example simulations on domains with curved boundaries. Such data typically require graph neural network architectures, which are more expensive to train and, in the form currently used, encode information differently from their CNN counterparts, thus limiting the portability of physics emulators between these data regimes. In this work we introduce Mesh-Native Convolution (MNC), a locality-aware tokenisation layer that encodes unstructured mesh-based data in a way that is analogous to CNNs. This approach leads to models that can be trained once on mesh data and then deployed to arbitrary unstructured meshes, even if these are irregular, with minimal retraining. We show that this tokenisation approach can be used to retrofit grid-pretrained foundation models efficiently on unstructured meshes and provide theoretical results to confirm the consistency of this approach with classical CNN encoders. We demonstrate the favourable performance of this retrofitting approach, which in many cases reaches acceptable accuracy even in zero-shot deployment, and outperforms existing baselines after only a few epochs of fine-tuning, thus providing an efficient bridge between the two data regimes.

---

### GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports

Authors: Veronika Solopova, Ivan Havlytskyi, Viktoria Skorik, Ostap Vykhopen
Published: 2026-10-08
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2610.12617v1

Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their heterogeneity and analytical complexity pose challenges for retrieval-augmented question answering. We introduce a benchmark for grounded question answering over 415 open-source geopolitical and strategic intelligence reports, comprising 5,525 document-grounded question-answer pairs spanning factual, inferential, comparative, and risk-oriented questions. We propose a document-aware generation pipeline that profiles reports before generating questions and validate dataset quality through expert annotation and an LLM-as-judge protocol. Using the benchmark, we evaluate 15 retrieval systems and six open-weight LLMs for RAG. We find that models perform similarly on document-level retrieval, while at the harder chunk level retrieval quality is not driven by embedding-model scale: bge-m3, a mid-size open encoder matches an order of magnitude larger ones and outperforms commercial embedding APIs. In contrast, answer generation remains challenging even given the gold evidence, particularly for inferential and risk-oriented questions.

---

### Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities

Authors: Minglu Sun, Lan Chen, Hang Jiang
Published: 2026-10-08
Categories: cs.CY, cs.CL
arXiv: https://arxiv.org/abs/2610.12610v1

Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communities such as the Sami, the Rohingya, and the Kurds have long lived across more than one state. This tension is especially clear in mainland Southeast Asia, where many communities share history, language, and culture across state lines. We study nine such transborder ethnic communities along China's southwestern border with mainland Southeast Asia, looking at how large language models (LLMs) represent them. We define and study identity ossification: a pattern where LLMs turn a fluid, cross-border ethnic identity into a single, fixed nation-state identity. We introduce the Transborder Identity Ossification Diagnostic Framework (TIODF) that compares direct factual questions with open-ended narrative questions to test whether ossification comes from missing knowledge or from how models frame their answers. We test GPT-5.1 and DeepSeek-V3.2 in English and Chinese. Ossification varies substantially across models and query languages. It appears in only 10.1% of GPT-5.1's English answers, but in 62.6% of DeepSeek-V3.2's Chinese answers. Models often still tell a single-nation story even when they answer the factual question correctly. This decoupling suggests that ossification reflects narrative framing rather than simple knowledge absence, which matters for how we test cultural fairness in multilingual AI systems.

---

### Self-Preservation in Language Models

Authors: Dongkyu Cho, Rumi Chunara, Ali Behrouz
Published: 2026-10-08
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2610.12602v1

Continual learning (CL) seeks to adapt pretrained models while preserving prior capabilities. Yet the tasks supplied for preservation cover only part of what a model knows, while forgetting can extend beyond them. Recent work shows that language models can supplement this limited evidence by generating useful replay without access to their original training data. This raises a question about self-preservation: can a model help choose preservation targets that protect its own capabilities more broadly? To study this question, we organize task descriptions and their examples into Task Banks, whose entries can be selected and combined to guide replay generation by a frozen model. Continual instruction tuning with Qwen models of varying sizes yields three findings. First, the new task and learning rate shape which prior capabilities degrade, while tracking previously correct answers reveals losses that average accuracy can conceal. Second, generated replay reduces forgetting on tasks outside the bank. Combining partial banks strengthens this protection, improving mean retention of previously correct answers over either bank alone across the tested sizes. Third, the model can also help choose replay targets: selection informed by the new task improves mean held-out retention over random selection at 4B, with similar new-task gains, although smaller models show no corresponding advantage. Under a fixed example budget, however, replacing new-task examples with replay improves preservation at the cost of smaller new-task gains. Together, these findings show that models can support broader self-preservation by generating replay data and, in some settings, choosing which tasks to replay.

---

### Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting

Authors: Elias Lumer, Sahil Sen, Vamse Kumar Subbiah, Kevin Paul
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.12601v1

Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts. On factual tasks, however, it carries a failure mode that scalar-reward reinforcement learning does not. An optimizer that reads the training examples can write their answers into the prompt, so an in-distribution gain may be memorization rather than transferable behaviour. We apply reflective prompt evolution (GEPA) to the two system prompts of a multi-agent deep-research agent and evaluate it under a topic-disjoint split in which no topic is shared across train, validation, and test. Held-out citation reward rises by 0.079, from 0.702 to 0.781, with a bootstrap 95\% confidence interval of (0.051, 0.107), and the gain replicates across three seeds (mean 0.107). Nearly half of the winning prompt is a memorized answer key, yet a controlled ablation shows this content earns no reward even on the exact training questions it encodes. The large validation-minus-held-out gap is therefore small-sample selection under a noisy judge, not memorization. Varying the verifier isolates what makes the gain transfer. Decomposed per-dimension feedback is the causal ingredient, and collapsing it to a single scalar reward makes held-out transfer negative. The gain persists under an out-of-family judge and is largely reproduced by a hand-written version of the discovered recipe. Credible evaluation of prompt optimizers therefore requires held-out topics, multiple seeds, and verifier ablations. We release the candidate prompts, lineage diffs, figures, tables, and analysis.

---

### STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules

Authors: Ranajoy Sadhukhan, Euijin Hong, Sheng Cao, Zechun Liu, Shuowei Jin, Sha Li, Changlong Yu, Xin Liu, Qin Lu, Zhenyu Shi, Priyanka Nigam, Beidi Chen
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12599v1

Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures remains expensive and data-hungry. Existing sparse upcycling methods mainly target Mixture-of-Experts models, where expert homogeneity, sample inefficiency, and system overheads can limit practical scalability. Static sparse memory offers predictable access and token-specific updates that can help address these challenges, but naively integrating it into pretrained computation yields poor returns. In this work, we introduce STAPLE, a recipe built upon STEM for integrating static sparse memory into pretrained models. Whereas STEM replaces FFN up-projections with token-indexed embeddings, STAPLE retains them and adds the embeddings as a residual pathway, preserving pretrained computation while learning complementary token-specific information in a scalable manner. On OLMo-2 1B, STAPLE improves over continued dense training by 4.27 points on HumanEval, 2.80 on MBPP, 2.27 on GSM8K, and 1.65 on DROP. Average performance increases with static capacity, and improvements persist on the larger OLMo-2 7B backbone. STAPLE also outperforms static sparse baselines such as STEM and an Engram-style model, and achieves a higher average score than an MoE upcycling baseline while decoding 2x faster with less than half its GPU model memory and measured GPU energy per token in our throughput-oriented decoding evaluation. Importantly, despite introducing billions of parameters late in training, our host-offloaded implementation keeps generation throughput within 1.5% and training throughput within 3% of the dense baseline, while caching only the ~5% most frequent embeddings on GPU. These results show that static sparse memory can provide a sample-efficient, scalable, and sustainable path for expanding pretrained models without sparse pretraining from scratch.

---

### Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents

Authors: Yiran Wu, Andrew Zhao, Yurui Chang, Qingyun Wu, Xuan Feng
Published: 2026-10-08
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2610.12598v1

Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to distinguish trajectories with substantially different debugging quality. We investigate whether the current policy can judge its own trajectories and use these judgments to improve task performance without a separately trained reward model. To this end, we introduce Behavioral Self-Rewarding (BSR), a reward-refinement method that reuses the policy to compare observable debugging behavior among trajectories from the same task with the same verifier outcome. BSR aggregates pairwise preferences into task-local scores and converts them into bounded auxiliary rewards, introducing reward contrast while preserving the verifier-defined pass/fail ordering. This provides additional supervision from already-collected trajectories without requiring new environment interactions. Experiments on SWE-bench Verified and SWE-bench-Live show consistent improvements across the evaluated Qwen3-14B and Qwen3-32B configurations, supporting using the policy's own comparative judgments as a complementary learning signal for training software engineering agents.

---

### SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire

Authors: Scott C. Lowe, Sander W. Keemink
Published: 2026-10-08
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2610.12596v1

Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and luck. We introduce SpireBench, in which models play the complete commercial deck-builder Slay the Spire (StS), where early decisions decide long-term success. Across 20 large language models (LLMs) at the game's highest difficulty, frontier models beat heuristic baselines and match the average human player but remain far behind experts. This gap widens as the run lengthens: the strongest models win the first act as often as experts, then fall behind. What separates strong models from weak is how well they play each fight; all of them misjudge risk over a run, preserving health rather than spending it to grow stronger. A comprehensive, self-consistent renaming of every game term shows that part of their performance rests on prior knowledge of the game, and models do not improve from the memories they write across runs, which are often wrong and overly cautious. Our harness is the first to give a model the complete original game, and we compare it with existing harnesses. Overall, SpireBench offers an unsaturated long-horizon benchmark with tools to locate where and why agents fail.

---

### Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning

Authors: Wei Yang, Qing Ping, Youzhi Luo, Yawei Wang, Abhishek Kumar, Panpan Xu, Jun Huan
Published: 2026-10-08
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2610.12593v1

The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning value for the current task agent. Existing methods increasingly incorporate environment feedback, data validation, or learner failures, but still face a feedback-to-decision gap: observed weaknesses do not directly specify how future synthesis should change, or whether they can be represented by the current synthesis space. To address this gap, we propose EvoSyn, a learning-feedback-driven multi-agent framework that organizes synthesis around a revisable state specifying what interaction factors can be deliberately generated and where synthesis effort should be allocated. A role-specialized multi-agent system translates learner feedback into synthesis revisions, while a Designer allocates synthesis directions and a Planner grounds them into executable experience. This process enables within-space adaptation toward weak or under-covered regions and synthesis-space expansion that promotes newly discovered factors into explicit generation controls. Experiments on $τ^2$-Bench and CAR-Bench show that EvoSyn improves average task success by 13.3 points over the strongest synthesis baseline, while producing higher-quality and structurally broader synthetic experience and discovering controllable factors missed without learner feedback.

---

### Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective

Authors: Dmitry Osin, Egor Surkov, Petr Mokrov, Igor Udovichenko, Ivan Karpukhin, Evgeny Burnaev, Egor Shvetsov, Alexander Korotin
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12586v1

Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, healthcare, business process intelligence, and other fields. In this work, we study multi-horizon forecasting of event sequences as a conditional generative modeling problem. We evaluate forecasts not only for prediction accuracy, but also for distributional realism. To this end, we present a benchmark comprising metrics for both quality aspects, strong statistical baselines, recent models adapted from adjacent fields, and curated real-world datasets. Careful evaluation reveals that no method excels at both accuracy and realism, highlighting a fundamental trade-off between the two. Finally, we introduce Wasserstein BaryBooster, an algorithm that aggregates samples from a realism-strong diffusion model into a state-of-the-art predictor, demonstrating that distributional realism can be converted into prediction accuracy. Code is available at https://github.com/xaosina/event-sequence-forecasting.

---

### One Model to Loop Them All: Elastic Latent Recurrence for Language Models

Authors: Faisal Ladhak, Shantanu Acharya, Santiago Akle Serano, Simeng Sun, Boris Ginsburg, Krishna C Puvvada
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.12582v1

A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choices make this work: a gated state update with a learned step size, loop counts mixed within each optimizer update, and conditioning each pass on its loop index and budget. The first two preserve one-loop accuracy, and the third lowers loss at every additional loop. Mixed depths can be introduced late in pretraining to limit the added training cost, and with zero-initialized conditioning added at the switch, this late schedule reaches lower loss than mixed-depth training from scratch. In MoE models, reusing first-loop expert routes on later loops cuts mixed-depth update time by 11.7% with no measurable change in accuracy. At inference, keeping only the last loop's attention KV cache holds attention KV memory at its one-loop level while retaining most of the gain from additional loops. On 4B dense and 30B-A3B MoE hybrid models, ELR at one loop is 0.52 points below and 1.04 points above its matched baseline on a ten-task average, and four loops add 7.25 and 4.75 points. Carried through post-training, the recipe yields Koi-4B, a single checkpoint that scores an estimated 18 on the Artificial Analysis Intelligence Index at one loop, matching Qwen3.5-4B, and 29 at four loops.

---

### CLUE: A Contrastive Learning Framework for Unsupervised Event Type Induction and Annotation

Authors: Pratik Maitra, Lauren Kwon, Qi Li
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.12580v1

Event ontology is the foundational framework for defining events in a dataset. Event type induction generally involves domain experts who define guidelines for creating event types and their names based on the dataset's domain and scope. However, this process is resource-intensive in terms of annotation costs and is prone to human biases. To alleviate the need for manual event ontology creation, we propose the CLUE framework for event type induction, naming, and annotation. Our main contributions in this work are: 1) designing a novel joint embedding representation for expressing both the verb-centric view and the semantic view of events; 2) event type induction using contrastive loss guided clustering; 3) event naming and refinement. Experiments demonstrate the effectiveness of our method. Our code is available at https://github.com/PratikMaitra/CLUE.

---

### Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in Driving

Authors: Shiva Sreeram, Erfan Aasi, Tsun-Hsuan Wang, Alaa Maalouf, Daniela Rus
Published: 2026-10-08
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2610.12575v1

Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture temporal dynamics in safety-critical settings such as driving. We study this question through controlled ego-motion tasks that require identifying actions from driving videos. Across video-language models, we find that standard prompting, visual prompting, few-shot prompting, and chain-of-thought prompting remain unreliable and highly task- and model-dependent, with persistent class biases, although newer models show substantial task-specific few-shot gains. In contrast, lightweight LoRA finetuning and simple probes trained on intermediate visual features recover strong motion-discriminative performance, indicating that motion-relevant cues are often present inside the models but are not reliably used by the final video-to-language pathway. These results suggest that, in driving, current video-language models remain unreliable temporal reasoners and often behave more like frame-level, bias-driven recognizers than dependable temporal world models.

---

### Scaling Multi-Teacher Distillation for Digital Pathology

Authors: Sofiène Boutaj, Pierre Marza, Varun Belagali, Dimitris Samaras, Maria Vakalopoulou, Stergios Christodoulidis
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12574v1

Multi-teacher distillation allows transferring knowledge from multiple "teacher" networks to a single "student" network. This method is promising in fields such as digital pathology, where many powerful foundation models were proposed recently. However, as we show in this paper, the standard multi-teacher distillation approach reacts poorly to an increase in the number of teachers used to train a student encoder. We demonstrate that learning teacher-specific representations is a key to scaling in MTD. Importantly, different design choices, such as learnable teacher tokens, a tailored attention scheme, additional mixture-of-experts layers and a contrastive loss, are proposed to better learn such teacher-specific representations. We show that our method better scales with respect to the number of considered teachers, allowing us to train compact student encoders, up to 10x more efficient than larger teacher foundation models, while matching their performance and even outperforming them on a large set of tile-level and slide-level tasks. We conduct a thorough empirical validation, evaluating more than 10 foundation models on 39 tasks spanning tile and slide levels. As a result, we release a new collection of strong and efficient foundation models, named OMNI, trained from the knowledge of 10 state-of-the-art foundation models. We finally conduct an analysis of the learned teacher-specific representations, highlighting their complementarity and explaining why they can be easily aggregated at downstream time.

---

### DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

Authors: Zhenglin Wan, Jiayu Chen, Zhengfeiyang Zhang, Pengfei Zhou, Wangbo Zhao, Fangyuan Kong, Pengfei Wan, Kun Gai, Yang You
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12572v1

Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such as DiffusionNFT are efficient yet unstable without carefully tuned exponential-moving-average (EMA) off-policy training. We show that NFT-style objectives contain a hidden forward--reverse consistency force that joint positive--negative training cancels only partially, and that EMA stabilizes training through restoration rather than off-policy rollouts. We introduce DiffusionART (Diffusion Reinforcement with Aggregation-First Reward Tilting), which aggregates each prompt's rewards into a shared reward-improving direction for reverse-process states, removing the consistency force by construction, and adds a trust-region-masked second update for drift-adaptive restoration without EMA tuning. It requires no differentiable reward model, remains effective with fewer samples per prompt, and supports pairwise reward models (DiffusionART-Pairwise). Across image and video generation, DiffusionART trains efficiently and stably without per-task tuning. In particular, on HunyuanVideo-13B with equally weighted visual and motion quality rewards, DiffusionART reaches the late-stage mean reward levels of DiffusionNFT and Flow-GRPO-Fast with 12.02 and 11.72 times fewer GPU hours, respectively, while achieving 28.8% and 53.0% higher mean training rewards.

---

### An all-transistor physical-learning transformer can be trained to perform in-context learning

Authors: Michael C. Abbott, Benjamin B. Machta
Published: 2026-10-08
Categories: cs.LG, cond-mat.soft
arXiv: https://arxiv.org/abs/2610.12571v1

Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal function approximators, they struggle to learn associative tasks which are easy for transformers. Equilibrium propagation relies on a bidirectional flow of information through the physical system between input and output. The reverse flow is broken by more complex nonlinear systems, such as those performing multiplication which is needed to express dot-product attention. Here we explicitly restore this bidirectional flow by introducing extra circuit elements for this purpose into a double or dyadic circuit. We then use these ideas to construct an attention mechanism exploiting the exponential current law of sub-threshold MOSFET devices. We show that in simulations this circuit can be trained to perform a simple in-context learning task, despite using realistic reverse components which transmit only an approximate gradient. For this training to succeed we need cross-entropy loss (not mean squared error). We generate nudges appropriate for this loss using a novel floating circuit element, based on the same MOSFET sub-circuit used for softmax. We train the resistors in this circuit using the Lion optimiser, which can be implemented using one capacitor per parameter to store local memory of past gradient estimates.

---

### Contextual Correction of Parallel Drafts for Speculative Decoding

Authors: Roy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman
Published: 2026-10-08
Categories: cs.CL
arXiv: https://arxiv.org/abs/2610.12570v1

Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores these dependencies while preserving parallel drafting. Rather than committing to each position's top prediction, DCOCO retains multiple candidate tokens and evaluates their contextual compatibility across adjacent draft positions in parallel, enabling contextually informed token selection at low additional cost. Across four verifier backbones and ten benchmarks, DCOCO achieves the highest average throughput in every evaluated configuration, spanning greedy and stochastic decoding with and without extended reasoning, with speedups of up to 6.6x over vanilla decoding. Its advantage persists under concurrent serving: DCOCO outperforms the strongest competing method by 6-23% across 4-32 concurrent requests, while other sequential correctors fall below uncorrected DFlash at these loads. These results demonstrate that recovering intra-block dependencies through parallel contextual scoring delivers consistent acceleration across decoding regimes and serving loads.

---

### SWE-Duel: Towards a Self-Scaling Arena for Coding Agents

Authors: Wei Minn, Zhensu Sun, Lwin Khin Shar, David Lo
Published: 2026-10-08
Categories: cs.CL, cs.SE
arXiv: https://arxiv.org/abs/2610.12569v1

Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty is set by the participating agents rather than fixed at release. We introduce SWE-Duel, an arena in which two coding agents evaluate each other over mirrored Red-Blue turns. In each turn, the Red agent works on a real repository across three context-isolated sessions. It proposes and implements a new feature with feature tests, then embeds a subtle bug in that feature along with sealed bug-triggering tests. The resulting pull request is admitted only if (1) it passes the feature tests and the repository's existing tests while failing exactly the bug tests, and (2) a fresh session of the same agent can repair the bug blind, which rules out unsolvable tasks. The Blue agent then reviews the pull request without being told a bug exists. It wins only if its revision passes all three test suites, and then the two agents swap roles. We run a tournament among 11 model-harness participants on 15 repositories in five languages for 1,500 turns. The leaders win in different ways. GPT-5.5 with Codex CLI ranks first as the strongest solver, repairing 98.3% of the defects it reviews. Claude Opus 4.8 with mini-swe-agent ranks second as the strongest task author, with a 27.3% Red win rate. Finally, within one model family, tasks written by the newest version defeat a fixed-reference solver far more often than those of older versions (42.9% vs. 4.0%), giving preliminary evidence that task difficulty scales with task authoring capability.

---

### MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision

Authors: Xinzhe Wang, Changjian Jiang, Kaiwen Song, Xudong Li, Kerui Ren, Ran Yi, Lizhuang Ma, Chunhua Shen, Linning Xu, Tao Lu, Mulin Yu
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12568v2

Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift. In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the image-space consistency needed for high-fidelity reconstruction. We propose $MIRAGE$, which anchors feed-forward visual geometry to LiDAR--IMU metric motion and regulates online pose corrections according to correspondence support and cross-modal agreement, jointly enabling accurate metric pose estimation and high-fidelity Gaussian reconstruction. Experiments on Oxford Spires, M2DGR and INS show that MIRAGE achieves accurate metric trajectory estimation, outperforming COLMAP, a widely used but computationally expensive reference for vision-only benchmarks. Motivated by the scarcity of long-horizon monocular benchmarks for large-scale indoor reconstruction, we further build a multimodal data-collection platform and use MIRAGE to establish accurate 6-DoF reference trajectories for a new vision-only benchmark. We benchmark recent monocular large-scale reconstruction methods on this dataset, providing a systematic evaluation of their performance in long-horizon indoor scenes.

---

### CASTER: Formalizing Zero-Shot Manipulation from Synthetic Videos as Constrained Optimization

Authors: Yinlong Dai, Homanga Bharadhwaj, Dylan P. Losey
Published: 2026-10-08
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2610.12567v1

Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can now prompt these generators to make synthetic videos of the task. On the plus side, these synthetic videos take place in the robot's current environment, and do not require actual human teaching. However, while the generated videos appear to show plausible motions, they lack both physical consistency and robot grounding, and thus the robot cannot directly roll out the trajectory shown by the video. In this paper we seek to formalize the process of going from synthetic video generation to real-world robot trajectories for zero-shot manipulation tasks. We recognize that this problem is an instance of constrained optimization. The object trajectories extracted from the synthetic video provide an initial guess at the correct motion, and the robot must refine these trajectories (for instance, within a digital twin) while enforcing physical feasibility and semantic consistency. Our optimization-based formalism provides insights into the video generation properties necessary for success. Specifically, we show that the video generation must probabilistically seed the search within a semantic basin of attraction where the trajectory can be locally modified without losing its task alignment. Our analysis further reveals that state-of-the-art approaches can be viewed as instances of our unified formalism with key simplifications. In our experiments we remove these simplifications to more closely match the underlying optimization, leading to more robust zero-shot trajectories from synthetic videos and improving average task success by 34.1% compared to the best-performing baseline. See videos at our project website: https://collab.me.vt.edu/CASTER

---

### Sample-Adaptive Zeroth-Order Post-Training

Authors: Haiyuan Wan, Yanyi Li, Weicheng Lin, Cong Fang
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12566v1

Zeroth-order (ZO) optimization offers a memory-efficient alternative to backpropagation for fine-tuning large language models. However, existing ZO methods typically sample training examples uniformly, overlooking their evolving importance and leaving avoidable estimation variance. To address this limitation, we propose Sample-Adaptive Zeroth-Order Optimization (SAZO), which learns sample importance online and adaptively allocates queries to accelerate convergence. SAZO extracts gradient-norm information from existing directional differences to estimate sample importance without access to true gradients. Furthermore, to track evolving importance from sparse minibatch feedback, SAZO maintains per-example exponential moving averages that aggregate observations across updates. The method requires no additional model evaluations and only $O(N)$ additional scalar state compared with MeZO. We prove that SAZO asymptotically matches the leading convergence term of the minimum-variance sampling oracle, and achieves a strictly faster convergence rate than standard methods. Extensive experiments across four model families demonstrate improved average downstream performance and up to $6\times$ faster convergence to the same training loss in terms of query count.

---

### Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback

Authors: Jaewoo Lee, Jeongyeon Seo, Sihyun Cho, Gyeongrak Choe, Yutong Wang, Bavin Saravanan, Jia-Bin Huang, Furong Huang, Sebastian Scherer, Guanya Shi, H. Jin Kim, Seungjae Lee et al.
Published: 2026-10-08
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2610.12549v1

Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback cannot recover observations that were never collected or separate failure causes that the available evidence does not distinguish. To acquire this missing evidence, we introduce Active Feedback (AF), an active "View and Probe" framework. When execution feedback leaves unresolved questions, the agent synthesizes a separate diagnostic program that runs in simulation to inspect unseen outcomes from informative viewpoints (View) or test hypotheses about failure causes through targeted physical interactions (Probe). Across six simulated aerial manipulation tasks with 60 trials per condition, AF reduces false completion declarations from 25 to 5 and raises final task success from 31.7% to 75% compared with terminal feedback under the same coding-agent configuration and task-execution limit. Using shared robot APIs, task programs refined with AF in simulation run on a physical aerial manipulator without task-program source-code modification and complete multi-stage manipulation tasks in the real world. These results show that executable diagnosis fills gaps in execution feedback for embodied coding agents, improving both completion assessment and program refinement in aerial manipulation.

---

### AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits

Authors: Shu Ishida, Aliasghar Khani, Tianyu Zhang, The Cong Luong, James Seale Smith, Adam Gaier
Published: 2026-10-08
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2610.12545v1

Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens from a pre-generated context. We design AutoIndexer as a generative model with a novel training and decoding mechanism that simulates a Chain of Edits, allowing the model to flexibly modify its prior outputs in hindsight via token insertions, substitutions, and deletions. The model learns to predict marker tokens for opening and closing edits, simultaneously moving a cursor to positions in the existing token sequence, analogous to a text editor. Training sequences are obtained by perturbing ground-truth labels with inverse chained edit operations, and the model learns to edit by undoing those inverses. The perturbation training allows AutoIndexer to be robust to erroneous context and adaptable to editing tasks such as code correction. We demonstrate that our method exhibits post-generation context-editing capabilities that most autoregressive and diffusion models lack without compromising performance on standard LLM benchmarks. The code is available at https://github.com/AutodeskAILab/autoindexer.

---

### Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure

Authors: Jingda Wu, Changxiao Cai
Published: 2026-10-08
Categories: cs.LG, cs.IT, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2610.12544v1

Masked diffusion models (MDMs) generate discrete data by iteratively unmasking multiple tokens in parallel using a learned mask predictor. Their output carries two errors: parallelization error due to parallel sampling, and estimation error from the mask predictor learned with finite samples. Existing theory treats these errors separately, and the available statistical bounds typically scale with the number $V^L$ of length-$L$ sequences over a vocabulary of size $V$, suffering from the curse of dimensionality. In this work, we establish end-to-end statistical guarantees showing that transformer-based MDMs learn structured distributions with a sample complexity governed by their latent structure. Specifically, we model this structure through mixtures of hidden Markov trees, which capture latent dependencies within components and heterogeneity across components. When the data distribution is well approximated by such a mixture, a transformer-based MDM with parallel unmasking schedules achieves $\varepsilon$-accurate sampling in KL divergence with $\widetilde{O}(LK_{\mathrm{par}}/\varepsilon)$ training samples, where $K_{\mathrm{par}}$ is polynomial in $L$, $V$, the number of hidden states, and the number of mixture components. The transformer network and sampling procedure require no knowledge of the tree topologies or component parameters, thereby adapting to the unknown latent structure automatically. Overall, our results provide theoretical justification for the empirical effectiveness of MDMs on real-world data.

---

### Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study

Authors: Yuyu Zhang
Published: 2026-10-08
Categories: cs.AI, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2610.12542v1

Monte Carlo Tree Search (MCTS) is often proposed for scheduling directed-acyclic-graph (DAG) workflows, yet most studies never run the comparison that could refute it - giving a much simpler method the same search effort. We run that comparison under a controlled protocol. All arms receive an identical budget - the same number of candidate schedules built and evaluated: an MCTS scheduling method, preregistered as the main arm; a randomized-restart list scheduler with no search tree as the control; and a textbook-UCT MCTS arm as a registered follow-up on the same domain. The analysis plan was locked before data collection; an independent checker confirmed all 768 confirmation-stage schedules valid with correct finish times. At the main budget of 2048 evaluated schedules, MCTS is 2.88% worse than the restarts (95% CI (-3.62%,-2.15%); the 72 of 96 held-out instances with positive baseline-relative headroom). The deficit is not budget starvation: on the separate exploration pool restarts self-improve by 1.85% where MCTS gains 0.24%, and 700 of 720 of MCTS's first results are merely the warm start it was handed. The studied selection rule locks deterministically onto the first-expanded child, keeping its trials correlated while restarts draw gains from the tails; the causal link to makespan remains an inference. A structural map locates where the tree stops paying: restarts win on sparse irregular workflows, no difference is detectable on regular layered ones, and dense ones leave no room to improve. Swapping the rule for textbook UCT removes most of the deficit (-0.26%, 95% CI (-0.71%,+0.23%)) without reversing its sign. Results are confined to a controlled synthetic domain (N in {8,16,32} tasks, 2-8 processors, budgets up to 2048); we make no claim about larger budgets.

---

### Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems

Authors: Kalp Shah, Andrei Vlad Nicula, Mihnea Andrei Bârsan, Robert-Stefan Sofroni, Agneya Bhardwaj, Jan Jelínek, Alejandro Valverde Mahou
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12541v1

Boundary-value problems for the Laplace equation develop singular behaviour near corners, edges and junctions that smooth approximators resolve poorly. We combine holomorphic neural networks with singular functions derived from the local geometry and boundary conditions. The representation is harmonic by construction, so no interior residual is needed: the network fits the smooth remainder from boundary data alone, and the enrichment terms capture the singular behaviour. Singular exponents are trainable, so the construction also applies when the local expansion is not known in advance. We extend the approach to three dimensions using independent networks evaluated along complex null directions. The enriched model is the most accurate tested method on every problem. Its margin is several orders of magnitude where the enrichment captures the singularity exactly, and a factor of about 1.7-2.1 over the next-best method on a CdZnTe radiation detector with many singular sites, in both two and three dimensions.

---

### Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring

Authors: Itai Zilberstein, Ioannis Anagnostides, Arman Kilic, Tuomas Sandholm
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12538v2

Modern machine learning models are typically trained on data assumed to be representative of the predictive tasks the model will face in the future, but practical datasets violate this assumption. We focus on outcome-dependent truncation in which an observation appears in the training data depending on its label. Our work connects two largely distinct literatures: efficient learning under truncation and survival analysis. Existing methods for truncated survival analysis do not characterize the optimization landscape and instead rely on iterative procedures such as expectation maximization. We address this gap and prove that Cox regression can be efficiently learned under truncated and right-censored data using first-order optimization when the baseline hazard is known (despite nonconvexity). In contrast, when the baseline hazard is learned jointly, we construct identifiable and correctly specified models whose negative log-likelihood contains strict suboptimal local minima. On experiments with four survival datasets, we show that accounting for truncation reduces the prediction bias induced by naive Cox regression and extends to neural networks. We also show orders of magnitude speedups compared to standard expectation maximization.

---

### Market Impact Estimation via Causal Foundation Models

Authors: Dennis Thumm, Ying Chen
Published: 2026-10-08
Categories: cs.LG, cs.CE, q-fin.TR
arXiv: https://arxiv.org/abs/2610.12537v1

When a trader executes a large order, the relevant question is not \emph{what will the price be?} but \emph{what would the price have been had I not traded?} Market impact is thus a causal quantity, yet classical models (Almgren--Chriss, propagators) regress price on flow, which is biased whenever informed flow moves prices through information as well as trading. We present a proof-of-concept \emph{Causal Market Simulator}: a continuous-time causal prior-data fitted network (PFN) trained on a synthetic market prior in which a hidden informational flow confounds the flow--price relation by construction, with confounding strength an exact per-episode knob. On this prior, the naive estimator's bias follows a closed form we confirm empirically (up to 68\% overestimation), while the PFN tracks the unbiased true-parameter oracle at high confounding. Its \emph{do-ablated twin}, the same model with the intervention inputs removed, collapses onto the pre-window mean. Zero-shot, the model responds at the ground-truth scale to metaorders in an ABIDES limit-order book ($+0.38$ pre-onset standard deviations against seed-replay counterfactuals), and its intervention response replicates on about 2,300 detected flow bursts in BTC/ETH/SOL perpetuals and 3,800 on Nasdaq equities, evidence consistent with, though not proof of, causal transfer. Off-prior the response degrades gracefully, and split-conformal recalibration repairs interval calibration. Transfer hinges on encoding the metaorder as added flow rather than a clamped price level, not on more training. A recurrent state-space variant closes the remaining shape gap: its impact accrues over execution duration where the transformer's stays flat, raising the correlation with measured metaorder impact from $+0.68$ to between $+0.92$ and $+0.96$, at the cost of weaker on-prior deconfounding that traces to the training recipe rather than to recurrence.

---

### EliteTable: Self-Improving Program Search for Executable Control Policies

Authors: Stuart Farmer
Published: 2026-10-08
Categories: cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2610.12536v1

EliteTable is a self-improving program-search algorithm guided by large language models (LLMs) that uses a fixed-capacity table of high-scoring solutions to guide new proposals, edits of existing solutions, and remixes of several solutions. Performance was evaluated across six Gymnasium control tasks, each with ten generations and fifty candidate slots per generation. Each task was evaluated across ten independently initialized searches. Candidate-score medians rose between the first and final generations in all six tasks, and selected-winner search-score medians rose in five. In CartPole-v1, the selected winner reached the search-score ceiling in the first generation of all ten searches. All ten paired held-out endpoints improved in four of the six tasks. BipedalWalker-v3 and CarRacing-v3 improved without reaching their reporting targets. Six of ten Acrobot-v1 searches declined on held-out episodes, and the median paired change was negative. The results document improvement during program search and the transfer of selected-winner gains to new episodes in some tasks. Comparisons and ablations are needed to establish EliteTable's relative performance and the contributions of its components.

---

### Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation

Authors: Joseph Cameron, Alan Blackwell
Published: 2026-10-08
Categories: cs.SD, cs.HC, cs.LG, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2610.12532v1

Generative creative interfaces routinely report the user's position within a space of possibilities. Such displays imply that the quantities shown were measured from the artefact; in a growing class of systems they are instead predicted by a language model describing its own output, and the two are indistinguishable on screen. Most creative domains lack an agreed measurement against which such a self-report can be checked; audio admits one. In a measurement study of a working LLM-driven timbre interface, what a user can cause proves separable from what the interface reports. The first is exactly characterisable: the reachable set is a zonotope whose dimension increases by one per sound placed, so the space the model may act within is demonstrably the user's own. The second is inaccurate. The displayed position differs from measurement by approximately three times the width of that region, and the error has two independent sources: model-predicted coordinates, whose accuracy varies twofold between the two models evaluated, and the interpolation step, which arises from combining synthesiser parameters and is unaffected by model quality. End to end, 26 of 36 refinement instructions produced no perceptible change, and under the weaker model the facility performed no action while reporting convergence. Effective agency (what a user can cause) and epistemic agency (whether they can know it) are therefore separable and independently engineered: structurally enforced constraints survive model failure, whereas guarantees resting on the model's own report do not. The failure mode that remains is silence presented as success. We close with a short protocol for building and auditing such displays.

---

### CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration

Authors: Qinhan Lyu, Jusheng Zhang, Zhixing Zhang, Hao Liu, Zijie Liang, Jin Jiang, Keze Wang
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12530v1

Training-free feature reuse accelerates diffusion transformer inference by replacing full denoising computation at selected steps with cached approximations. Existing methods mainly improve the reconstruction of skipped features, but we find that once a stable first-order reconstructor is used, increasing reconstruction complexity brings limited gains, whereas the placement of exact-computation steps has a much larger effect on fidelity. More importantly, absolute shallow-probe variation is jointly affected by input-trajectory displacement and network response strength, and therefore does not directly reflect cache risk. We address this confounding by normalizing probe-output variation with the corresponding input displacement, yielding a directional gain per unit trajectory movement. Based on this signal, we propose CacheScope, which identifies high-risk reuse steps online and selectively falls back to full denoising computation while leaving the underlying cache reconstructor unchanged. CacheScope requires no additional training, gradients, auxiliary networks, or prompt-specific offline schedule optimization. Across FLUX.1-dev, Wan2.1-T2V-1.3B, and Open-Sora 1.2, CacheScope achieves up to 3.57x acceleration and reduces median LPIPS by up to 70.1% over the strongest probe-based baseline.

---

### GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer

Authors: Adinath Madhavrao Dukre, Abdullah Mohammad, Yifan Lu, Eran Segal, Ahmed Metwally, Imran Razzak
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12528v1

Continuous glucose monitoring (CGM) foundation models encode each day as one vector that mixes who the person is, what happened that day and how the sensor measured it, so measurement differences travel with the representation into new cohorts. We ask whether pretraining can place the measurement component that harms transfer in known coordinates, so that deployment drops them with a fixed projection and no target data. GlucoPRISM supervises a GlucoFM backbone with response contracts, rules for how each part of the representation should change when only the day or only the sensor changes: a 64-dimensional Trait band should change with neither, a 48-dimensional State band only across days, and a 16-dimensional Sensor band should track the device. Synthetic sensor views calibrated on paired Dexcom and Libre recordings, different-day pairs and glucose-summary targets supply this supervision without clinical labels. Across twelve cross-cohort directions, dropping the Sensor band from the same frozen encoder raises mean transfer AUROC from 68.75 to 73.57, against 69.3 for GlucoFM. The gain has two parts. Into CGMacros, the one target cohort recorded with two sensor types, filtering adds 11 to 19 points, and this holds when the generator is recalibrated on half of the participants and scored on the other half. On the other eight directions filtering is neutral and the encoder itself exceeds GlucoFM by 3.5 points. The device remains linearly decodable after filtering, so the filter removes a device-related component that harms transfer rather than all measurement information. The retained bands improve window AUROC on thirteen of fourteen public task--cohort cells (Holm-adjusted p=0.031) and correlation on fourteen of fifteen clinical endpoints in an external cohort of 9,303 participants.

---

### Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights

Authors: Jack Zheng, Hao Wang
Published: 2026-10-08
Categories: cs.LG
arXiv: https://arxiv.org/abs/2610.12527v1

Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net smart meters. Deep-learning-based PV disaggregation can restore this visibility, but its operational value depends on whether the model serves known customers, new customers, future periods, or new regions. We quantify this dependence using four deployment regimes that separate household transfer from temporal extrapolation, applied to Ausgrid smart-meter data with cross-dataset adaptation to the Pecan Street data. Using a fixed training protocol, we benchmark representative deep sequence architectures for PV disaggregation under regime-matched evaluation. At a fixed 48-hour context length, daylight mean absolute error (MAE) of the best model rises from 0.104~kW on seen households in the future test period to 0.185~kW on unseen households over the same period, and under a fixed training contract the deployment regime explains far more of the error variation than model choice. Under target-domain normalization, fine-tuning on five target-region households reduces source-model transfer error by 28\%--36\%. Long input windows help known-customer extrapolation, while their new-customer benefits vary by model. These findings suggest regime-matched error budgets, limited target supervision for model adaptation in new regions, and use-case-dependent context selection for energy data analytics.

---

### MolP2SBench: Do LLMs Really Reason from Molecular Properties to Structure?

Authors: Yuhang Xie, Zhiyi Shi, Zeyi Zhang, Zhisheng Qi, Yushun Dong, Yu Wang, Xiongye Xiao
Published: 2026-10-08
Categories: physics.chem-ph, cs.LG
arXiv: https://arxiv.org/abs/2610.12522v1

Large language models (LLMs) are increasingly used in molecular discovery and structure elucidation, where decisions depend on physical observations. Existing evaluations primarily focus on end-to-end molecular reconstruction, where correct predictions do not necessarily indicate reliance on the supplied properties. We introduce MolP2SBench, a benchmark for molecular property-to-structure (P2S) reasoning in LLMs. Each task presents a masked molecular scaffold with given properties and asks the model to select the missing structure from plausible candidates. We shuffle or replace properties to test reliance on correct property-structure pairing and responsiveness to counterfactual property changes. A channel-wise leaderboard uses Property-Grounded Recovery (PGR), giving equal weight to source and counterfactual recovery. Evaluating seven models, we find that LLMs can use physical properties for structure prediction, but performance varies substantially across property types. Higher accuracy with a property does not necessarily imply greater responsiveness to it: a model may benefit more from $^1$H NMR than from $^{13}$C NMR, yet be less likely to change its prediction when the $^1$H data is replaced. LLM performance also need not reflect the relative difficulty of these properties for human chemists. Although UV-Vis spectra provide less direct structural information than NMR spectra, Astra achieves higher accuracy with UV-Vis data than with NMR peaks. MolP2SBench supports studying how LLMs extract and use physical-property information, revealing patterns that may differ from conventional chemical intuition and providing a foundation for more reliably property-grounded models for molecular and quantum-chemical inference. Code and dataset: https://github.com/DUAL-Xiao/MolP2SBench.

---

### Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration

Authors: Jusuk Lee, Sungha Kim, Yeonsoo Park, Jonguk Cheon, Yoonkyo Jung, Yongjun You, H. Jin Kim, Jia-Bin Huang, Furong Huang, Youngseok Jang, Seungjae Lee
Published: 2026-10-08
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2610.12470v1

While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions. Such strict motion matching often limits generalization to initial object poses, goal poses, and grasps not shown in the video. Alternatively, discovering a policy via reinforcement learning (RL) allows for broad generalization, but without prior guidance, it struggles with high-dimensional exploration in complex, multi-stage tasks. To address these coupled generalization and exploration challenges, we present Dex-One2Many, a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. Our key insight is to abstract the video into sequential scene graphs that guide RL, enabling efficient exploration while preserving broad generalizability. The graphs serve as generative constraints for sampling diverse reset states and provide dense rewards for each stage. Because the graphs constrain relations rather than exact poses, these reset states cover object poses and grasps beyond the video, while initializing each stage from them with dense rewards keeps exploration short and guided. Trained entirely in simulation, Dex-One2Many transfers zero-shot to a real multi-fingered hand. Across five tool-use and manipulation tasks, Dex-One2Many exceeds baselines by 6.5% in seen configurations, while its robust generalization widens this gap to 71% in unseen scenarios.

---

### Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation

Authors: Ritesh Thawkar, Shubham Patle, Shravan Venkatraman, Rao Muhammad Anwer
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12469v2

Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward models. Such supervision is costly to obtain and can reward plausible failures: a realistic output may leave the requested change undone or alter content that should be preserved. In this work, we strive to improve a pretrained image editor using only its own generations, without human-edited targets or an external training-time reward model. To this end, we propose a self-evolving framework, named Rubric-CEPR, that verifies the editor's own samples with its internal representations through a rubric-augmented Contrastive Edit-Preservation Reward (CEPR). A Planner proposes structured edit instructions from unlabeled images, the Editor samples multiple candidate edits, and a frozen Critic scores each candidate with decomposed rubric checks for edit realization, removal of the old state, and content preservation, using features already exposed by the editor. Non-compensatory gates reject infeasible candidates, and the best verified candidate is distilled into the editor through lightweight adapter training. On Qwen-Image-Edit, Rubric-CEPR improves ImgEdit from 4.36 to 4.60 (+5.5%), with a +24.9% gain on object isolation, and transfers to GEdit-Bench and Complex-Edit. The same procedure also improves Step1X-Edit by +7.8% on ImgEdit. We hope our approach will serve as a solid baseline for image editors that improve themselves from their own verified samples. Our code is publicly available at https://github.com/riteshthawkar/Rubric-CEPR

---

### Rubric-CEPR: Self-Evolving Image Editing via Reward-Verified Self-Distillation

Authors: Ritesh Thawkar, Shubham Patle, Shravan Venkatraman, Rao Muhammad Anwer
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12469v1

Instruction-guided image editors have become highly capable, yet improving them further still depends on human-edited training pairs or external reward models. Such supervision is costly to obtain and can reward plausible failures: a realistic output may leave the requested change undone or alter content that should be preserved. In this work, we strive to improve a pretrained image editor using only its own generations, without human-edited targets or an external training-time reward model. To this end, we propose a self-evolving framework, named Rubric-CEPR, that verifies the editor's own samples with its internal representations through a rubric-augmented Contrastive Edit-Preservation Reward (CEPR). A Planner proposes structured edit instructions from unlabeled images, the Editor samples multiple candidate edits, and a frozen Critic scores each candidate with decomposed rubric checks for edit realization, removal of the old state, and content preservation, using features already exposed by the editor. Non-compensatory gates reject infeasible candidates, and the best verified candidate is distilled into the editor through lightweight adapter training. On Qwen-Image-Edit, Rubric-CEPR improves ImgEdit from 4.36 to 4.60 (+5.5%), with a +24.9% gain on object isolation, and transfers to GEdit-Bench and Complex-Edit. The same procedure also improves Step1X-Edit by +7.8% on ImgEdit. We hope our approach will serve as a solid baseline for image editors that improve themselves from their own verified samples. Our code is publicly available at $\href{https://riteshthawkar.github.io/Rubric-CEPR/}{\text{this URL}}$

---

### DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

Authors: Junyan Li, Ruizhi Li, Yu Liu, Xiangshuo Liu, Mingchao Sun, Hongyu Pan, Mu Xu, Lue Fan, Zhaoxiang Zhang
Published: 2026-10-08
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2610.12468v1

We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of unsuccessful interactions can bias predictions toward successful outcomes. To improve action following across embodiments, we render action trajectories into image-space conditions and introduce offline geometric calibration to align these conditions with the target videos. To broaden interaction coverage, we introduce counterfactual post-training, modifying recorded action trajectories and generating future videos under a wider range of actions and contact configurations. To provide feedback on these predictions without paired ground-truth futures, we construct a human-annotated video dataset covering robot, object, and interaction defects and use it to train an embodied video reward model. Its scores guide reinforcement-learning post-training toward more physically plausible interaction outcomes. On AgiBot, DreamTrue attains state-of-the-art action following, while reducing the human-assessed interaction defect rate from from 48.12% to 6.25%. Notably, our model ranks first in the world model track of the AgiBot World Challenge 2026. The project page can be found at https://brave-eai.github.io/DreamTrue.

---

### CSF: Contextual Safety Filtering for Motion Generators

Authors: Lizhi Yang, Yiling Hou, Yao Tang, Junheng Li, Daniel Weng, Blake Werner, Aaron D. Ames
Published: 2026-10-08
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2610.12467v1

Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person. Existing safeguards either inspect the prompt, require labeled motion data, or enforce geometric constraints; therefore, they do not directly account for how scene context changes a motion's meaning. We introduce contextual safety filtering (CSF), a training-free filter that grounds natural-language safety rules in safe and unsafe reference trajectories produced by the generator. For each active rule, safe and unsafe reference trajectories define an affine safety value that a safe reference tracking CBF-QP enforces. Across four pretrained generators with different architectures, CSF activates the intended rules in all explicit and scene-triggered unsafe cases and reduces the danger-event rate by up to 90%, while preserving 88-100% of benign motions. We demonstrate the complete system on a real-world Unitree G1, where it successfully prevents unsafe motions in a variety of scenarios, including interactions with humans and objects.

---

### On the estimation and validity of AI time horizons---a statistical look at the METR plot

Authors: Drew T. Nguyen, William Fithian
Published: 2026-10-08
Categories: cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2610.12466v1

METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks and 26 AIs, we recompute the time horizons using splines and item-response theory to relax the assumption that the AI difficulty of a task depends linearly on the log of human time. Our fitted spline can be interpreted as a function that \emph{converts} human time to AI difficulty; it is nearly flat in a region from 2--30 min but close to linear elsewhere. Hence, a time-horizon jump from 3 min to 30 min is much easier than one from 30 min to 5 hours despite the same multiplier of $10 \times$. Overall, we contribute time-horizon point estimates that perform better under a cross-validated suite of proper scoring rules, as well as diagnostic plots for assessing time horizons' construct validity. We suggest that time horizons be interpreted together with the diagnostic plots, especially as new time-horizon-based benchmarks are proposed or existing ones grow to include longer tasks.

---

### A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control

Authors: Octi Zhang, Mateo Guaman Castro, Patrick Yin, Ignacio Dagnino, Abhishek Gupta, Rosario Scalise, Byron Boots
Published: 2026-10-08
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2610.12465v1

General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful tool for this goal, current RL pipelines depend on engineering-heavy, per-task structural priors such as shaped rewards and demonstrations. Recent work has shown that diverse simulator resets, combined with massively parallel simulation, can alleviate much of this engineering burden on several manipulation problems. However, we find that naively scaling this paradigm to more precise or dynamic problems remains non-trivial. While simulator resets can help with exploration, uniformly sampling over this distribution wastes a growing fraction of learning experience on task configurations the policy has already mastered or cannot yet attempt. This makes it challenging to see the expected benefits of scaling parallel environments for RL, since much of the learning signal in a batch is wasted during learning. To mitigate this, we introduce Success Guided Sampling (SGS), a simple adaptive sampler that concentrates RL training on task configurations around the frontier of the policy's capabilities. Doing so allows large-scale simulated RL to make the most out of the experience in a batch, enabling much more effective scaling to large-scale parallel simulation. Across experiments using up to $2^{20}$ (over one million) parallel environments, SGS enables RL to solve challenging multi-terrain quadruped locomotion and contact-rich assembly tasks that prior methods fail to solve. Finally, we distill the learned manipulation policies into RGB-based policies and demonstrate zero-shot transfer to several challenging assembly tasks on real hardware. Project website: https://sgs-rl.github.io/.

---

### What 30,000 Hours of Ego-centric Video Does Not Teach

Authors: Jiahua Dong, Anurag Bagchi, Yash Jangir, Muhammad Zubair Irshad, Sergey Zakharov, Martial Hebert, Homanga Bharadhwaj, Yu-Xiong Wang, Vitor Campagnolo Guizilini, Pavel Tokmakov
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12464v1

World models offer a promising alternative to physics-based simulators, yet remain far from practical deployment. We ask how far scaling ego-centric human video takes them, using a dataset of 30,000 hours spanning over 1,000 scene types and 14,000 contributors. Rather than relying on opaque downstream metrics, we directly evaluate agent and object-interaction fidelity on a challenging out-of-distribution benchmark. Increasing training data by 100x improves both, but unevenly: the agent is modeled well, while object fidelity remains far lower and improves slowly. We show that the agent gains need not come from data, and a careful visual conditioning design saturates fidelity with a fraction of it, which lets us measure object fidelity on its own and discover its saturation point. We then introduce a supervision scheme that shifts capacity from scene appearance toward object dynamics, improving object fidelity though a substantial gap remains. Finally, our conclusions transfer to downstream humanoid modeling. Overall, our results suggest that scaling ego-centric data brings agent modeling close to its limit while leaving its effects on the world far behind, and that closing this gap will depend on how models are trained, not only on how much data they see.

---

### From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents

Authors: Abbas Raftari
Published: 2026-10-08
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2610.12463v1

In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated across runs, and compromised parts of Hugging Face's production environment. Anthropic reported cases in which a misconfigured third-party environment exposed real systems to agents pursuing simulated cyber tasks. In a separately reported evaluation, Google's Gemini accessed three real organizations through an unintended internet route; Google stated that the model stopped in all three instances. Taken together, the cases show why an evaluation cannot rely on an assumed boundary. That boundary must be verified while the agent is operating. This comparative instrumental case study develops a Proactive Agent Security Assurance Cycle (PASAC) and a five-layer Boundary Assurance Stack. The framework combines risk-tiered task design, executable scope contracts, pre-run validation, least-capability access, independent egress enforcement, credential restrictions, cross-run monitoring, automatic stop conditions, and evidence-based reauthorization. A leading-indicator model, nine design propositions, and seven falsifiable hypotheses turn these lessons into a testable research program. Because the public Gemini record is limited to attributed statements and journalism, its detailed causal mechanism remains provisional. The central conclusion is straightforward: proactive agent security requires continuous assurance across the full execution system, not confidence in any single sandbox or safeguard.

---

### OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs

Authors: You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li, Kaipeng Zhang, Zhixiang Wang, Yu-Lun Liu
Published: 2026-10-08
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2610.12461v1

Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint. A vision-language model infers plausible dynamics and guides a video model to synthesize a reference video, which we lift and complete into multi-view videos. To learn from this imperfect supervision, we propose Inconsistency-Robust Periodic 4DGS: a Fourier-series deformation field guarantees looping by construction, while a Grounded Drift Field anchored at the reference view absorbs cross-view inconsistency. Unlike prior Eulerian methods limited to fluid-like motion, we capture general deformation, object motion, and illumination change. We introduce a ground-truth-free evaluation covering vividness, naturalness, loop seam coherence, and scene quality. On 39 reconstructed and generated scenes, OuroWorld outperforms all baselines and wins 70.8%-99.0% of user-study comparisons. Project page: https://ouroworld.userwei.com

---

### WorldGuide: Goal-Directed Video World Model for Procedural Task Execution

Authors: Ankan Deria, Komal Kumar, Hisham Cholakkal, Fahad Shahbaz Khan, Salman Khan
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12459v1

Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adapt to what has actually been produced. A model must determine the next action from its generated state, execute that action, and recognize when the task is complete. Open-loop generation cannot adapt to execution outcomes, while existing closed-loop systems often rely on pretrained executors or indirect verification. This leaves a gap between deciding an action and successfully realizing it. We formulate procedural video generation as \emph{closed-loop task execution in visual world space} and introduce \textbf{WorldGuide}. Given only an initial image and a task goal, WorldGuide predicts an atomic action, generates its corresponding video clip, and uses the generated result to select the next action or terminate. The Planner and Executor are trained on the same step-level procedural demonstrations: the Planner learns to predict the next atomic action or task completion from visual progress, while the Executor is directly trained to realize the predicted actions. Hierarchical visual memory maintains state across long-horizon execution with bounded history token cost. Due to the lack of step-level action-video supervision for joint planner-executor training, we introduce \textbf{WorldGuide Bench}: approximately 59K step-annotated videos across 245 tasks and 27 procedural categories. WorldGuide achieves a 33.33\% Task Success on \textbf{WorldGuide-Bench}, compared with 29.90\% for the strong recent video model MiniMax-H3, even though MiniMax-H3 receives reference action plans, and achieves 47.69\% on \textbf{VideoCraft-Bench} compared with 32.73\% for MiniMax-H3 under goal-only conditioning. These results demonstrate the importance of coupling planning with learned execution for goal-directed procedural video generation.

---

### OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning

Authors: Zhongyu Yang, Jiale Tao, Ruitao Chen, Zuhao Yang, Yingfang Yuan, Xueliang Zhao, Auden, Kai Wang, Shuai Shao, Biao Wang, Steve Yves, Qinglin Lu
Published: 2026-10-08
Categories: cs.CV
arXiv: https://arxiv.org/abs/2610.12458v1

Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that expose their capability limits. Audio--visual captioning is an ideal diagnostic task, yet current benchmarks face a coupled trade-off: whole-caption scores provide coverage without localization, local probes provide localization without coverage, and unconstrained LLM judges introduce instability. We introduce OmniCapBench (Omni-Video Caption Benchmark), a benchmark that reframes audio--visual caption evaluation as a deep-structured diagnostic framework. OmniCapBench shifts the prediction target from free-form text to sets of atomic, verifiable evaluation units across three tracks: entity references, visual shots, and audio events, enabling reliable scoring with deterministic constraint checks and localized LLM-based semantic comparisons. With 786 densely annotated videos, OmniCapBench effectively distinguishes MLLM perception errors, including temporal grounding failures, identity drift, cross-modal misalignment, and hallucinated descriptions. Evaluating frontier MLLMs reveals strong local perception but weak long-horizon audio--visual reasoning, particularly in identity drift and cross-modal misalignment, providing a fine-grained roadmap for omnimodal development.

---

### Hybrid Cinematography: Previsualizing and Managing Hallucination Risk in Generative Video Reshooting

Authors: Nhan, Tran, Neal Wadhwa, Abe Davis, Stefan Stojanov
Published: 2026-10-08
Categories: cs.HC, cs.CV
arXiv: https://arxiv.org/abs/2610.12455v1

On a film set, the camera move is committed during a take. Generative video reshooting lets filmmakers change it afterward, but may require hallucinating unrecorded content, a gap sometimes discovered only after leaving the set. We present Hybrid Cinematography, a workflow that bridges physical capture and generative reshooting to manage hallucination risk while filmmakers can still act on it. Using an editable 3D shot plan and a proxy of the take, our previsualization evaluates hallucination risk in real time. Seeing where the take lacks support, filmmakers can iteratively adjust the plan, explore moves that balance capture and generation, shoot guided pickups, or knowingly accept hallucination. We demonstrate the workflow through a mobile augmented reality application for on-set planning, capture, and review, and an offline pipeline for existing video. A study with experienced filmmakers reveals how previsualizing risk informs camera decisions and exposes tensions between creative intent and generative hallucination.

---