Few-Shot
-
Reinforcement learning to improve large language model-based automated code compliance systems
2026-10-29 14:37:41Jack Wei Lun Shi, Minghao Dang, Wawan Solihin, Justin K. W. YeohAbstract
Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucinated computer-processable rules. This paper introduces P4IR, a two-stage framework that uses supervised fine-tuning (SFT) to instill domain knowledge in an LLM, followed by Group Relative Policy Optimization (GRPO) to improve the accuracy of the generated intermediate representations in the form of high-level code skeletons. The framework achieved final reductions of up to 21.3% and 41.0% in tree edit distance and token-level Levenshtein distance respectively, relative to the SFT baselines. Comparative analysis demonstrates that this approach in a zero-shot setting outperforms leading LLMs in both code structure and semantics, evaluated via few-shot prompting. Additionally, the GRPO stage produced a statistically significant reduction in false positives. By combining SFT with GRPO to optimize directly for domain-specific objectives, this approach offers a path toward more accurate and reliable LLM-based ACC systems.
Abstract (translated)
URL
https://arxiv.org/abs/2606.22402
PDF
-
AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
2026-10-28 19:30:40Haotian Zhai, Tianming Sha, Junnan LiAbstract
Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LLM prompting that produces a whole plan in a single serial reasoning process. These approaches depend on linguistic common sense, commit to a plan from the initial instruction, and only update after failures, which weakens robustness and state awareness. We present AtomTree, a hierarchical framework for state-aware task planning with LLMs. AtomTree incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further decompose or to output a grounded low-level action. A lightweight memory module summarizes past outcomes for reuse in later decisions. When a low-level action stalls, AtomTree triggers hierarchical backtracking replanning to return to the parent node and regenerate the subtree plan from the latest state, preventing continued drift along an incorrect trajectory. In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38744
PDF
-
Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting
2026-10-28 10:09:11David Rawlinson, Gideon KowadloAbstract
There is a fundamental contradiction between the desire for models that can generalize, and models that can continuously adapt to recent input with changing statistics. These conditions, captured in few-shot and continual learning settings, can bias or disrupt learned representations. This harms generalization to a broader context, leaving the model unable to overcome input variance. This paper proposes a solution based on the Complementary Learning System architecture (CLS), in which a Short-Term Memory (STM) delegates generalization to a slow, statistical Long-Term Memory (LTM). Delegation is achieved by working in a space of robust, generalized perceptions produced by the LTM. With this separation, the STM can focus on memorizing recent input and avoiding interference between memories. We show that on an image classification task, the resulting CLS model is more resistant to forgetting in a domain-incremental continual learning setting than a baseline ResNet LTM, and generalizes more effectively in a few-shot setting than other continual learners. In the continual setting, overall accuracy is slightly worse than existing continual learning models, but with a different mix of performance characteristics. Results analysis suggests that the model is limited by the representations and representational plasticity of the LTM. In future work, we will seek to address this by replaying STM memories to the LTM.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38577
PDF
-
Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning
2026-10-28 10:05:41Wenqi Li, Xiangjue Dong, Sulaiman VesalAbstract
Large audio language models (LALMs) can process speech directly, but it remains unclear how well they use the non-lexical acoustic information that speech carries. We study this question through pain, using TAME-Pain, which contains pain-neutral Harvard sentences and spoken pain ratings recorded at different self-reported pain levels. We introduce HEAR, a four-stage diagnostic framework that traces pain-related information from the speech signal to the model's prediction, and apply it to seven closed-source and open-weight LALMs. On the Harvard sentences, where pain can only be inferred from the voice, all models perform at chance level, and same-speaker references or few-shot examples improve balanced accuracy by no more than six points. On the spoken ratings, the same models reach 87.5-99.7% balanced accuracy. Layer-wise probing of open-weight LALMs shows that pain can be decoded from early audio representations (74.1% balanced accuracy for binary prediction and 45.0% for three-class severity), but that this information, along with most pain-associated acoustic cues, decreases in deeper layers. In an acoustic perception test, weaker models cannot distinguish even large changes in these cues, whereas stronger models can but still fail to infer pain. Finally, we recover pain-related acoustic cues and directly reinject them as structured text into the prompt, which improves pairwise pain prediction by up to 32 points. These results indicate that current LALMs encode paralinguistic information in early layers that is largely unavailable when the model produces its answer.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38570
PDF
-
Are Seismic Foundation Models More Than Glorified Feature Extractors?
2026-10-27 21:54:33Laura Laurenti, David Liu, Brian Kulis, Men-Andrin Meier, Christopher JohnsonAbstract
Earthquake sequences are stochastic on two separated timescales: the seismic waves of any individual earthquake propagate over seconds to minutes, while the earthquakes themselves arrive as a sparse, self-exciting occurrence process, with inter-event intervals from seconds to months. Respecting both scales in one training objective is the open challenge. Foundation models (FMs) for seismic waveforms instead import their learning targets from audio and vision, where every target is computed from a single fixed-length window. Such a window holds one realization of the wave propagation (an earthquake trace), never the occurrence process that decides when earthquakes happen. We develop nine model designs sharing one Mamba encoder-decoder, trained on a fixed corpus of 3M windows, varying the self-supervised objective, quantization bottleneck and mixer; the two key comparisons are architecture-matched, varying the objective alone. Each checkpoint is evaluated frozen on three downstream tasks. Varying the target redistributes downstream skill rather than raising it, and no checkpoint wins everywhere. Adding masking pressure to our strongest classifier re-specializes it rather than making it a generalist: it gains 6.9 points of few-shot P-wave picking precision and loses 9.6 points of few-shot classification accuracy. By the standard imported from language and vision, these models are feature extractors rather than FMs. Controls on capacity, architecture, and domain proximity do not explain why skill moves rather than rises. Against task-specific baselines the advantage is regime-dependent: our checkpoints beat them few-shot on classification and ground-motion prediction, and trail them on full data. We argue the binding constraint is the target, and that settling the question requires a learning target defined across events, the timescale that makes seismicity stochastic in the first place.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38003
PDF
-
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
2026-10-27 17:58:52Igor Shilov, Xiaoxue Yang, Alexander Panfilov, Evgenii Kortukov, Matthieu Meeus, Peter Romov, Wojciech Samek, Jonas Geiping, Yves-Alexandre de MontjoyeAbstract
We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention between trusted and untrusted tokens, enabling models to reason over untrusted content without following injected instructions. We evaluate HoS on Llama-3.3-70B-Instruct and GPT-OSS-20B. We compare it against SecAlign++, a state-of-the-art finetuning-based defense, and ASIDE, a defense that, like ours, builds instruction-data separation into the model architecture. We show that HoS offers greater robustness to adaptive attacks, better performance on standard utility benchmarks, and matches top performance on standard agentic prompt injection benchmarks. More specifically, the black-box RL-Hammer attack reaches 97% ASR against GPT-OSS-20B and 85% against SecAlign, but only 10% against HoS. Claudini, a state-of-the-art white-box attack, strengthened against HoS through autoresearch, requires 3 times more FLOPs to reach the same ASR on HoS as it does on GPT-OSS-20B or SecAlign. HoS preserves base-model utility across standard multiple-choice benchmarks and prompting setups, whereas SecAlign and ASIDE degrade in few-shot settings. On agentic benchmarks with static attacks, HoS and SecAlign perform similarly and substantially improve the security-utility trade-off over the base model. ASIDE struggles with tool use, achieving only 10% utility. These results show that prompt injection robustness can be achieved and improved through targeted attention interventions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37657
PDF
-
An Algorithmic Account of Few-Shot Concept Induction in Language Models
2026-10-26 14:48:07Michael A. Lepori, Laila Johnston, Aalok Sathe, Zhuonan Yang, Roman Feiman, Ellie PavlickAbstract
Both models and minds not only encode features that describe an entity, but can specifically represent which features of that entity are relevant for a given context. This core capability underlies in-context learning in language models and a variety of cognitive phenomena in minds, yet it is unclear how intelligent systems identify and promote relevant features. In this work, we propose Amortized Direction Accentuation (ADA), an algorithmic hypothesis that provides an explanation for how relevance is determined in the context of few-shot concept induction --- the ability to infer a latent concept from a small number of positive examples. Under ADA, concept induction proceeds by forming a summary representation of the examples in a feature space that is shaped by amortized knowledge about which features tend to be useful for finding commonalities between items. We investigate and validate ADA in language models using a few-shot concept induction task. This work provides a novel perspective on the mechanisms supporting contextualization in language models and a promising hypothesis for a core aspect of cognition.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35533
PDF
-
Ranking Function Generation with LLMs for Termination
2026-10-26 14:41:52Rongkang Li, Jiaxin Hu, Taolue Chen, Yong Li, Fu Song, Zhilin WuAbstract
Ranking functions are a fundamental technique for proving loop termination, but constructing them manually is challenging and requires substantial expertise. We propose RAINFALL, a neuro-symbolic framework which follows the generate-verify-refine paradigm and tightly integrates LLMs with symbolic verification. RAINFALL formulates ranking function synthesis as a code-completion task by inserting placeholders into the input program and constraining the LLM to fill four predefined slots for each loop. The completed program is then checked by a symbolic verifier. If verification succeeds, a valid ranking function is obtained; otherwise, the verifier's diagnostics are translated into natural-language feedback that guides iterative refinement of the LLM's output. We evaluate RAINFALL on two public benchmark suites comprising 358 terminating C programs. Using MiniMax V2.7, RAINFALL synthesizes verifiable ranking functions for 323 programs (90.22%), outperforming all promising baselines. In particular, it solves 12 more programs than PROTON 2.1, the best-performing baseline and winner of the SV-COMP 2026 Termination category. Furthermore, combining RAINFALL with PROTON 2.1 increases the success rate to 96.65% (346/358 programs). We also conduct ablation study confirming individual contributions of placeholder contracts, few-shot examples, symbolic verification, and diagnostic information feedback. Experiments across LLMs further confirm the effectiveness of RAINFALL. Our results suggest a generic, sound framework for ranking-function synthesis and, beyond termination, LLM-assisted synthesis of formally checkable liveness certificates, both of which represent new directions of software engineering research.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35523
PDF
-
LE-GDA: Layer Ensemble Gaussian Discriminant Analysis for Training-Free Few-Shot CLIP Adaptation
2026-10-26 06:21:21Pavodi Maniamfu, Vogel Kiketa, Zezina Kuzulu Kuetu, Jakin Mukendi Kabongo, David Mayoya Kutangila, Pescie Honore Kinkani Mampuya, L'Or Wolo SiekaAbstract
Training-free few-shot adaptation of vision-language models typically constructs a classifier from CLIP's final projected image representation, leaving intermediate representations unused. Combining them is not straightforward. Class scores from different representations differ in spread by orders of magnitude for the same query. Direct averaging allocates influence by numerical scale rather than predictive information. We propose Layer-Ensemble Gaussian Discriminant Analysis (LE-GDA), a method that fits regularized shared-covariance discriminants independently to intermediate and final representations extracted in one frozen encoder pass. LE-GDA standardizes each discriminant's class scores per query, selects a small representation multiset on labeled validation data, and combines it with the zero-shot classifier without gradient-based optimization. Across 11 datasets, four CLIP backbones, five shot counts, and three independently sampled K-shot training sets, LE-GDA achieves the highest mean accuracy of all evaluated methods on every backbone, raising the 16-shot mean from 78.01% to 79.54% over a matched GDA-CLIP (final-feature) baseline and improving that baseline for every backbone-shot combination. At one shot, LE-GDA retains a 1.20-point mean gain over the baseline even though covariance estimation is unavailable and per-query standardization is neutral. A control with richer per-class structure inside a single representation does not reproduce the gain, indicating that the benefit comes from combining representations. These results show that intermediate CLIP representations carry information beyond the final embedding and can improve training-free few-shot adaptation. Code and evaluation resources are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34901
PDF
-
MedAdaptAgent: An Automatic Harness for Adapting Medical Imaging Models to New Sites
2026-10-26 05:56:00Hanxue Gu, Zhonghao Liu, Xingrui Gu, Kang Wang, Yang YangAbstract
Reusing pretrained medical-imaging models offers an alternative to training from scratch. A model trained for the same task may perform poorly at a new hospital because imaging protocols and preprocessing differ. Effective adaptation depends on the model architecture, domain shift, and available labels and compute. Adaptation can improve scores on a small labeled set yet reduce performance on unseen data. We present MedAdaptAgent, an automatic harness that turns a supplied model, target data, and a free-text request into a new-site adaptation workflow. Its LLM-driven Adaptation Planner uses model-site evidence to choose compatible experiments and revise subsequent adjustments. The harness requires evidence of improvement over the pretrained model, then delivers the selected model as a complete, runnable package. Evaluation spans 26 segmentation and classification transfers across architectures and compute settings, with segmentation annotation budgets ranging from zero-shot transfer to few-shot adaptation. With 20 local annotations, mean segmentation Dice rises from 0.483 to 0.774 across 10 transfers, a 60.1% relative gain, with no harmful replacements. Mean classification AUROC rises from 0.810 to 0.837 across 13 transfers, a 3.4% relative gain. Comparing adapted models with the pretrained model reduces harmful classification replacements by 30.8% versus selecting the highest-scoring model on the available labels, using identical candidates. Seven public-model deployments demonstrate adaptation and reproducible package delivery across contrast and modality shifts. A CT-to-MRI study extends the evaluation to four LLM planners, including two open-weight models. We release the code on GitHub.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34884
PDF
-
Seeing Before Naming: Context-Grounded Learning of Novel Visual Concepts
2026-10-26 04:55:38Gabriel Adineera, Jinoh KimAbstract
Learning an unfamiliar visual category requires more than adapting a classifier: the model must connect its visual evidence to a useful semantic name. A pre-trained vision-language model can retain discriminative image features while providing a weak textual anchor for the target concept. We address this imbalance through context-grounded semantic anchoring. Our framework, SynerNet, learns concept-specific name embeddings, exposes them to compatible linguistic contexts, and conditions their representations on visual evidence. Difficulty-aware processing and adaptive objective weighting coordinate this adaptation while retaining the pre-trained backbone. On four VISTA-Beyond domains, SynerNet reaches a mean 16-shot accuracy of 74.35%, compared with 72.45% for few-shot name learning. Across 14 domains in the name-masked transfer setting, it improves mean accuracy from 45.17% to 46.74%. Ablations identify concept-specific name embeddings and cross-modal context integration as important components. These results support treating concept acquisition as the construction of visually grounded semantic anchors.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34846
PDF
-
Recursive CLIP: Vision-Language Distillation with Looped Transformer Blocks
2026-10-25 21:07:02Szymon Mazurek, Alberto Presta, Micha{\l} ByraAbstract
Contrastive vision-language models such as CLIP typically rely on independently parameterized transformer blocks across depth. We investigate the extent to which these blocks can instead be reused recurrently while preserving the transferable capabilities of CLIP. We study recursive transformer backbones in which a small set of $N$ transformer blocks is applied $M$ times per forward pass. By holding $N \cdot M$ fixed to the depth of a standard ViT-B, our models preserve computational depth while progressively increasing parameter sharing. We consider two recursive CLIP model families: rCLIP, where only the vision encoder is recursive, and r$^2$CLIP, where recurrence is also introduced in the text encoder. We study these models under both direct contrastive training and through knowledge distillation from a strong ViT-B/16 teacher pretrained on DFN-2B, using the substantially smaller CC3M and CC12M datasets. We evaluate the resulting models on zero-shot classification and cross-modal retrieval, and further study their adaptability through few-shot learning, visual grounding, and concept unlearning. Our results show that CLIP can tolerate substantial recurrent block reuse, although its effect depends on the encoder and downstream task. Recurrence also provides parameter efficiency by construction, since fewer distinct transformer blocks need to be stored and adapted. Our results establish recurrent block reuse as a practical design space for vision-language models and highlight its implications for knowledge transfer, downstream adaptation, and parameter efficiency.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34563
PDF
-
Transformer to GPT-5: Advancements, Limitations, and Future Directions in Large Language Model Design
2026-10-25 13:25:30Harsidak Singh Banwait, Chander PrabhaAbstract
Large Language Models (LLMs) have revolutionized Artificial Intelligence (AI) by their extraordinary capabilities, like contextual understanding, few-shot/zero-shot learning, code generation, ability to reason and problem-solving. Recent studies have shown immense work on LLMs. Yet, there is limited work on the thorough taxonomy of LLMs. This study would showcase a detailed classification of LLMs, starting with the earlier models like BERT and leading to LLMs like GPT, Gemini, Claude and Grok. We would delve into topics like datasets used to train LLMs, computational power used during training, their hardware specifications, architecture and parameters. Further, we would also look at the limitations, computational challenges and open problems as well. This study would primarily focus on the timeline of LLMs, signifying their growth over the period. Findings reveal a clear pattern: models that optimize the ratio between architectural complexity and data quality exhibit stronger reasoning stability and better alignment, without proportionally increasing the computational load. This desired balance between scaling and sustainability is the defining characteristic of the current generation of AI.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34281
PDF
-
The Hitchhiker's Guide to System 1 Models: Fast Decision-Making Beyond LLMS
2026-10-24 16:26:01Haggai RoitmanAbstract
Large Language Models excel at reasoning and generation but their autoregressive, token-by-token inference makes them unnecessarily slow, expensive, and poorly calibrated for the many routine decisions (routing, gating, scoring, classification) that modern AI systems require at sub-second latency. A growing class of models addresses this gap: System 1 decision models, architectures that map an input directly to a typed, structured decision in a single forward pass. This guide provides a comprehensive, practitioner-oriented treatment of the field. We propose a five-family taxonomy covering encoder-based classifiers, reward models, non-autoregressive decision engines, contrastive decision models, and extraction models, and we provide in-depth coverage of each family's architecture, training methodology, and deployment trade-offs. A central theme is calibration: we develop the theory of proper scoring rules, analyze Reinforcement Learning for Calibrated Decisions (RLCD), and examine recently discovered phenomena including IIA violations, ordinal-scale bias, and few-shot recalibration under distribution shift. On the integration side, we describe how System 1 models serve as decision infrastructure within agentic workflows and System 1 + System 2 cascades that route between fast and slow models based on calibrated confidence. The guide covers 18 application domains, maps the rapidly growing open-source ecosystem (over 70 model reproductions in weeks), provides runnable code throughout, and includes a practitioner's checklist, an open-source model zoo, and 22 self-assessment questions with detailed answers. Spanning 190 references, it is intended as a unified entry point for researchers and engineers working at the intersection of fast decision-making, calibration, and production AI systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33775
PDF
-
Beyond Prompts: A Systematic Study of LLM-Based Machine Translation Evaluators
2026-10-24 15:30:59Dmitry Popov, Roman Bokhyan, Ekaterina Enikeeva, Artem Mekhraliev, Stepan Vysotsky, Nikolay KarpachevAbstract
LLM-based evaluators have rapidly become a standard tool for machine translation evaluation, yet the design choices that shape their behavior remain poorly understood. We present a systematic study of how instruction design, few-shot demonstrations, backbone model choice, and multi-step workflows affect span-level and ranking-based MT evaluation. We collect new expert RATE annotations on WMT24 and WMT25 English-Russian translations, with transfer validation on MQM- and ESA-annotated benchmarks across five additional language pairs. Our experiments reveal four robust findings: instruction structure shapes evaluator behavior, high-quality demonstrations matter more than quantity, frontier backbones exhibit distinct evaluator profiles (recall-, precision-, or ranking-oriented), and fusing outputs across diverse backbones outperforms single-evaluator multi-call setups. Although evaluator design exposes a large combinatorial space, several discovered design principles transfer consistently across annotation protocols and language pairs. We synthesize these findings into ORBIT, a family of LLM-based MT evaluators. Our strongest configurations achieve expert-level performance in error span detection and in Accuracy and Fluency ranking at roughly 20x lower cost than expert human annotation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33741
PDF
-
Component Pooling Trained Across Orientations for Few-Shot Remote Sensing Scene Classification
2026-10-24 07:50:46Bingchen Yan, Wenheng Guo, Yuye ZhouAbstract
Few-shot remote sensing scene classification (FSRSSC) aims to recognize novel scene categories from only a few labeled images. Most FSRSSC methods summarize the feature map of an image by global average pooling, which treats the few objects that define an aerial scene and the large background around them alike, and they rarely consider that aerial images have no canonical orientation. To address these issues, we propose RoCoP, a parameter-free component pooling network trained across orientations. RoCoP consists of a feature extractor, a non-negative decomposition module (NDM) and a component scoring module (CSM). NDM factorizes the local descriptors of each image into a few additive components with a deterministic initialization and a single multiplicative update, so that the positions of one object are grouped together. CSM weights each component by its activation magnitude and converts the weights into a soft mask for pooling. Because both modules are invariant to permutations of feature positions, the only rotation-sensitive part of the pipeline is the backbone, which we train to classify randomly rotated views of every image. Experiments on NWPU-RESISC45, AID and UC Merced show that component pooling and rotated-view training are complementary: together they improve a strong transfer-learning baseline by about 2.5 points in 5-way 1-shot accuracy on NWPU-RESISC45 and AID, without adding parameters at inference. Under an identical protocol, RoCoP outperforms re-implemented metric-based and task-adaptive methods, and NDM and CSM also improve existing methods when plugged into them. We further identify the regime in which the method does not apply, namely very small base sets.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33518
PDF
-
P2N: Reusing Deep Representations for Greater Effective Depth
2026-10-24 02:59:28Yiqin Hao, Boyi Zeng, Zitong Wang, He Li, Shixiang Song, Feichen Song, Yifan Liu, Ran Tao, Bryan Dai, Zhouhan LinAbstract
Mathematical problem solving and autonomous agents are increasingly important applications of language models, demanding stronger reasoning capabilities. Computational depth is a key resource for such reasoning, but adding model layers increases both training and inference costs, while test-time scaling incurs substantial additional inference computation. We introduce P2N (Previous to Next), which reuses the previous token's deep representations, already available during generation, to increase effective computational depth with negligible decoding overhead. Specifically, P2N adds the previous token's deep hidden state to the current token's shallow representation, allowing subsequent layers to build on previously completed deep computation. This recurrence extends effective computational depth across tokens, while introducing only a single vector addition per decoding step. We train the recurrence using parallel Jacobi updates restricted to a middle-layer core. Experiments with Qwen-style models show that, at 1.5B parameters, P2N improves GSM8K accuracy by over 10 percentage points under both zero-shot and few-shot prompting, with nearly unchanged decoding latency. The benefits also extend to language modeling and average performance on general downstream benchmarks. on general downstream benchmarks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25076
PDF
-
Tiny Recursive Policy: Recursive Latent Refinement for Visuomotor Control
Abstract
Behaviour cloning has become a powerful approach for robotic manipulation, but many modern policies reconstruct their internal representation from a fixed observation window at each prediction and do not maintain persistent latent context throughout execution. We introduce Tiny Recursive Policy (TRP), a parameter-efficient behaviour-cloning policy that combines persistent temporal state with recursive latent refinement. At each control step, TRP repeatedly updates high- and low-level latent states using a shared computation module before decoding an action sequence, and propagates the resulting state to subsequent predictions. We evaluate TRP across LIBERO-100, MetaWorld ML45, and the LIBERO-Mem benchmarks. TRP performs competitively across multi-task and few-shot settings and shows substantial gains on long-horizon and context-dependent tasks, while using significantly fewer parameters than large generative baselines. Execution-time perturbations show that reliance on the persistent carry increases with temporal-context demand, while training with carry perturbations substantially improves robustness to both carry and visual corruptions. Ablations reveal a strong interaction between persistent state and recursive refinement: the benefit of carry depends strongly on the amount of within-step computation, and the resulting performance cannot be explained by parameter count alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33288
PDF
-
Scaling Qualitative Analysis with Large Language Models: Development and Validation of the Smart Coder Framework for Human-LLM Collaborative Coding
2026-10-23 18:52:09Cheng Tang, Kun Wang, Yaxuan Yang, Shiyu Wang, Allan Cohen, Rachael Eriksen Brown, Chandra Hawley OrrillAbstract
Current uses of large language models (LLMs) for qualitative coding often rely on ad hoc prompting with limited guidance for reliability and human oversight. To address these limitations, we propose the Smart Coder Framework, a three-phase approach structuring human-LLM collaborative coding through Instruction, Prompt Strategy, and Reliability Check. We evaluated the framework using 72 middle-school mathematics teacher interview transcripts and a human-consensus benchmark. A factorial design compared instructed versus uninstructed prompts, few-shot versus few-shot plus chain-of-thought prompting, and single-pass versus self-consistency coding. Twelve transcripts were used for prompt development and calibration, and 60 for the formal evaluation. In the results, instruction consistently improved agreement. Chain-of-thought further improved agreement under adequate instruction, and self-consistency produced smaller, theme-dependent gains but helped identify unstable decisions for human review. Performance also varied by transcript characteristics. Overall, the framework systematically structures and monitors LLM-assisted qualitative coding while preserving human authority over coding decisions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33205
PDF
-
Flownomaly: Single-Step Conditional-Mean Recovery for Few-Shot Anomaly Detection
2026-10-23 17:53:30Bernardo Perrone Ribeiro, Erkut Akdag, Egor BondarevAbstract
Few-shot industrial anomaly detection requires modeling category-specific normality from only a handful of defect-free images. Common approaches tie inference to stored exemplars, impose rigid linear structure, or risk reproducing anomalous content. Flownomaly instead casts the problem as normal-counterpart recovery in frozen DINOv2 feature space. Given normal supports, a velocity field is learned through conditional flow matching over frozen patch tokens to transport Gaussian noise toward normal features. Along straight paths, a single recovery step using one evaluation of the optimal field yields the posterior mean of the clean normal token without trajectory integration. The operating time governs how strongly recovery modifies a query token. With no anomalous validation samples available for tuning, a normal-only Jacobian gain-to-noise criterion selects this time from the supports alone. Squared residuals between query tokens and their recovered counterparts yield anomaly signals for both dense localization and image-level detection. Across 1-, 2-, and 4-shot benchmarks on MVTec-AD and VisA, together with sample-shot evaluations on Real-IAD, Flownomaly achieves state-of-the-art performance against recent category-specific methods. In the 1-shot setting, image- and pixel-level AUROC reach 97.8% and 98.0% on MVTec-AD and 95.3% and 98.7% on VisA, with a 2.1-point image-level AUROC improvement over the strongest baseline on VisA. Code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32964
PDF
