paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

NeurIPS 2026

Refactoring Code Through Library Design

Žiga Kovačič, Justin Chiu, Celine Lee, Wenting Zhao, Kevin Ellis

Maintainable and general software allows developers to build robust applications efficiently, yet achieving these qualities often requires refactoring specialized solutions into reusable components. This challenge becomes particularly relevant as code agents are increasingly used to solve isolated one-off programming problems. We investigate code agents' capacity to refactor code in ways that support consolidation and reusability. We first investigate what makes a good refactoring, finding via simulation results and a human study that proxies of program size, such as Minimum Description Length, better predict preferable refactorings than extant software engineering metrics, such as Maintainability Index. We then present \textsc{Librarian}, a method that combines divide-and-conquer with sample-and-rerank to generate reusable libraries. We compare \textsc{Librarian} to state-of-the-art library generation methods, and study it on real-world Python programs.

NeurIPS 2026

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding

Xiang Fan, Yuheng Wang, Bohan Fang, Jason Ren, Ranjay Krishna

Image-to-video generation powers a vast array of downstream applications. However, while the de facto standard, ie, latent diffusion models, typically employ heavily conditioned denoising networks, their decoders often remain unconditional. We observe that this architectural asymmetry leads to significant loss of detail and inconsistency relative to the input image. To address this, we argue that the decoder requires equal conditioning to preserve structural integrity. We focus specifically on image-based generation tasks, where maintaining the structural and textural integrity of the source image is paramount. We introduce RefDecoder, a reference-conditioned video VAE decoder by injecting the reference image directly into the decoding process via reference attention. Specifically, a lightweight image encoder maps the reference frame into the detail-rich high-dimensional tokens, which are co-processed with the denoised video latent tokens at each decoder up-sampling stage. We demonstrate consistent improvements across several distinct decoder backbones (eg, Wan 2.1 and VideoVAE+) achieving consistent improvement on three reconstruction benchmarks. Notably, RefDecoder can be directly swapped into existing video generation systems without additional fine-tuning, and we report across-the-board improvements in subject consistency, background consistency, and overall quality scores on the VBench I2V benchmark. Furthermore, RefDecoder generalizes well to other visual generation tasks such as style transfer.

NeurIPS 2026

ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition

Abdulwahab Felemban, Yahia Battach, Faizan F Khan, Yuqian Fu, Xuhui Liu, Yesmeen Khattab, Yousef A Radwan, Xiang Li, Natalie Dunn, Susanne Bähr, Tullia I Terraneo, Fabio Marchese, Sara Beery, Burton H Jones, Francesca Benzoni, Mohamed Elhoseiny

Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated monitoring. Progress in data-driven coral analysis, however, is constrained by the scarcity of large-scale datasets with fine-grained labels that are taxonomically consistent across sites and studies. To address this gap, we introduce ReefNet, a large-scale public coral reef image dataset with point-level annotations mapped to the World Register of Marine Species (WoRMS) taxonomy. ReefNet aggregates imagery from 76 curated CoralNet sources and an additional reef site from Al-Wajh (Red Sea), totaling approximately 925K genus-level hard coral annotations. Through expert-driven verification and targeted filtering, we derive a high-confidence benchmark subset with 92% expert agreement over 39 hard-coral label classes, enabling reliable evaluation under realistic label noise and strong class imbalance. Beyond dataset construction, we establish a comprehensive benchmark spanning zero-shot, cross-domain few-shot adaptation, within-source evaluation, and cross-source transfer to the Al-Wajh dataset. Experiments with state-of-the-art vision–language models (VLMs), multimodal large language models (MLLMs), and vision-only backbones reveal substantial degradation in zero-shot and extremely few-shot regimes, while adaptation with in-domain supervision yields large gains yet still leaves a persistent gap under cross-source shift and on long-tail genera. These results highlight fundamental challenges in applying general-purpose multimodal models to biodiversity monitoring and underscore the importance of large-scale, taxonomically grounded, high-quality datasets. ReefNet serves as both a benchmark and a training resource for advancing fine-grained coral reef understanding. ReefNet data and trained models are provided on Hugging Face, and code for accessing and benchmarking the data is provided on GitHub.

NeurIPS 2026

Reduced Cost Influence Functions for Predict-then-Optimize under Noisy Data

William Zhang, Saurabh Amin, Georgia Perakis

Machine learning models deployed in decision-making pipelines, from vehicle routing to dynamic pricing to clinical decision support, must remain reliable in the face of low-quality training data. We study a predict-then-optimize setting in which an upstream model predicts the cost vector of a downstream linear program, with a large pool of noisy training data supplemented by a small curated set of clean data. We introduce Reduced Cost Influence Functions (RCIFs), which combine influence functions from robust statistics with the geometry of linear optimization to estimate how each training point shifts downstream decisions. Building on this, we propose a reweighting algorithm that uses RCIFs to downweight harmful training points and reduce downstream regret. Experiments on random linear programs and shortest-path problems show that our approach reduces regret, and accompanying theory characterizes properties of RCIFs and identifies regimes favorable to our method relative to baselines.

NeurIPS 2026

Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation

Erik Großkopf, Soumya Snigdha Kundu, Hendrik Möller, Nicolas Münster, Mehdi Astaraki, Paula T Buzduga, Kerstin Ritter, Benedikt Wiestler, Jan Kirschke, Jonathan Shapey, Tom Vercauteren, Florian Kofler

The Panoptic Quality (PQ) metric is the standard for jointly evaluating instance and semantic segmentation. However, its original definition relies on a One-to-One matching between predicted and ground truth segments, which is only straightforward when the IoU threshold exceeds 0.5. Below 0.5, multiple matching strategies emerge in a poorly explored problem space. We systematically elucidate this space by recasting segment matching as a constrained bipartite assignment problem. Independently bounding the prediction- and ground-truth-side degrees yields four matching strategies: One-to-One, Many-to-One, One-to-Many, and Many-to-Many. We show that the first three are well-defined within the PQ framework, while Many-to-Many falls outside it. These strategies become relevant when instances are fragmented, adjacent objects are difficult to delineate, or annotations are noisy. Central to our framework is a vertex-based accounting of TP, FN, and FP, anchored to ground truth and predicted segments rather than to matching edges. We further show that the framework extends naturally to part-aware panoptic segmentation, and we explore part-aware evaluation on biomedical data. Across configurable case studies we report how different combinations of thresholds and matching strategies behave in practice. We release a unified open-source package built on Panoptica. It exposes Voronoi-based region-wise analysis, part-aware evaluation, and Area Under Threshold Curve computations as configurable options.

NeurIPS 2026

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

Nail B Khelifa, Richard Turner, Ramji Venkataramanan

Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound finite-round error accumulation in the context of diffusion models, but two questions remain open:~what distribution does the recursion converge to, and how fast? We answer both, isolating a mechanism distinct from imperfect learning: even with perfect score estimation and exact sampling, the early stopping of the reverse diffusion (required for numerical stability) drives a progressive drift away from the data distribution. We prove that this recursion converges geometrically to a unique limiting distribution, which admits a closed-form characterization as an infinite mixture of increasingly Gaussian-smoothed versions of the data distribution. A Hermite spectral decomposition of this limit reveals that recursive training acts as a low-pass filter: higher-order modes, which encode fine non-Gaussian structure, are attenuated much more strongly than coarse modes. This spectral picture motivates annealed truncation schedules that progressively shrink truncation times across retraining rounds; we prove that any schedule converging to $0$ asymptotically eliminates recursive compounding. Finally, we show our idealized characterization is robust: in the presence of discretization and score estimation errors, the learned distribution remains in a Wasserstein-2 ball around the ideal limit, with mode-dependent contraction rates that contract high-order errors faster than low-order ones. We validate the theory on synthetic Gaussian mixtures and CIFAR-10.

NeurIPS 2026

Recursive Multi-Agent Systems

Jiaru Zou, Rui Pan, Ruizhong Qiu, Pan Lu, Shizhe Diao, Jindong Jiang, Hanghang Tong, Tong Zhang, Markus Buehler, Jingrui He, James Zou

Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principles from a single model to multi-agent systems, and ask: Can agent collaboration itself be scaled through recursion? To this end, we introduce RecursiveMAS, a recursive multi-agent framework that casts the entire system as a unified latent-space recursive computation. RecursiveMAS connects heterogeneous agents as a collaboration loop through the lightweight RecursiveLink module, enabling in-distribution latent thoughts generation and cross-agent latent state transfer. To optimize our framework, we develop an inner-outer loop learning algorithm for iterative whole-system co-optimization through shared gradient-based credit assignment across recursion rounds. Theoretical analyses of runtime complexity and learning dynamics establish that RecursiveMAS is more efficient than standard text-based MAS and maintains stable gradients during recursive training. Empirically, we instantiate RecursiveMAS under 4 representative agent collaboration patterns and evaluate across 9 benchmarks spanning mathematics, science, medicine, search, and code generation. In comparison with advanced single/multi agents and recursive computation baselines, RecursiveMAS consistently delivers an average accuracy improvement of 8.3\%, 1.2$\times$-2.4$\times$ end-to-end inference speedup, and 34.6\%-75.6\% token usage reduction.

NeurIPS 2026

Recursive Language Models

Alex Zhang, Tim Kraska, Omar Khattab

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose **Recursive Language Models** (**RLM**s), a general inference paradigm that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs can successfully process inputs more than an order of magnitude beyond model context window limits and, even for shorter prompts, dramatically outperform the quality of vanilla frontier LLMs and common long-context scaffolds (e.g., on GPT-5 by a median across the evaluated benchmarks of 26% against compaction, 130% against CodeAct with sub-calls, and 13% against Claude Code) across four diverse long-context tasks while having comparable cost. At a small scale, we post-train the first model around the RLM. Our model, **RLM-Qwen3-8B**, outperforms the underlying Qwen3-8B model by a median of 28% and even approaches the quality of vanilla GPT-5 on three long-context tasks.

NeurIPS 2026

Rectified Policy Rollouts with Hierarchical Expert Guidance for Neural Combinatorial Optimization

Wenzheng Pan, Nuoyan Chen, Jiaxi Liu, Jiale Ma, Junchi Yan

In the field of Neural Combinatorial Optimization (NCO), Reinforcement Learning (RL) stands out for its ability to naturally enforce complex constraints via its auto-regressive decision pattern. To mitigate the longstanding challenges, e.g., reward sparsity and sample inefficiency in the vast combinatorial action space which causes ineffective training, subpar performance, and poor scalability, we propose CORectifier, a novel NCO solver learned under the hierarchical gated rectification mechanism to regularize the arbitrary exploration: partial policy-predicted actions in a trajectory are probabilistically replaced with high-quality segments from reference solutions. CORectifier prompts the model with tri-level optimal signals, operating at the batch, instance, and sub-instance levels with fragments of diverse lengths injected at random decision steps. This Rectified RL (RRL) paradigm helps develop optimality-aware and sample-efficient RL learners while maintaining their sequential-decision manner for constraint satisfaction, delivering a new perspective to hybridize RL and SL/IL for NCO with improved utility rate of limited supervision. Sufficiently extensive experiments on Traveling Salesman Problem (TSP), Asymmetric TSP (ATSP), Prize-Collecting TSP (PCTSP), Capacitated Vehicle Routing Problem (CVRP), Knapsack Problem (KP), Job-Shop Scheduling Problem (JSSP), and Single Machine Total Weighted Tardiness Problem (SMTWTP), across synthetic and real-world benchmarks, show superior quality than RL baselines by up to 59.7%.

NeurIPS 2026

Recreating Video Arenas via Automated Preference Scoring

Yue Zhao, Aniket Gupta, Juze Zhang, Tiange Xiang, Ryan Rong, Xuan Su, Fei-Fei Li, Ehsan Adeli

Evaluating video generation models is notoriously challenging; existing metrics either fail to align with human judgment or rely on costly, unscalable human ratings. In this work, we introduce \textbf{Video Preference Score} (VPS), a fully automated video preference score designed to directly model human judgment and accurately recreate large-scale, Elo-based video arenas. Trained on a newly collected dataset that augments generated videos with retrieved real-world footage, VPS evaluates paired videos against complex text prompts to predict human preference. Experiments demonstrate that VPS correlates highly with human consensus and generalizes zero-shot across unseen models and benchmarks. Furthermore, we showcase the utility beyond evaluation: as a plug-in reward model, VPS seamlessly integrates with Flow-GRPO to improve WAN-2.1's generative quality by 51 Elo points. Overall, VPS provides a scalable and generalizable solution for both evaluating and aligning modern video generation models.

NeurIPS 2026

Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing

Jing Ma, Yujia Wu, Zhaoqiang Liu

We study the sample complexity of noisy one-bit compressed sensing for signals drawn from a prior distribution. By characterizing the effective distributional complexity of the prior via its approximate covering number, we prove that posterior sampling achieves accurate recovery with high probability when the number of measurements scales with the logarithm of the approximate covering number, up to a one-bit separation gap factor. This upper bound is robust to learned prior mismatch. Specifically, we show that posterior sampling with an approximate prior remains reliable, provided that the learned prior distribution is sufficiently close to the true signal distribution in Wasserstein distance. In addition, we establish a sample complexity lower bound for any reliable method of noisy one-bit compressed sensing, showing that our upper bound is nearly matched in its main prior dependent term. To approximate the ideal posterior sampling process for real world scenarios, we instantiate posterior sampling through a plug-and-play algorithm with diffusion priors. Experiments on the FFHQ and ImageNet datasets demonstrate the effectiveness of our proposed approach.

NeurIPS 2026

Recovering the Apresjan Hierarchy Using Linkage-Based Clustering

Maximilien Dreveton, Matthias Grossglauser, Daichi Kuroda, Patrick Thiran

Hierarchical clustering seeks to uncover nested structure in data by constructing a tree of clusters, whose deeper levels reveal increasingly fine-grained relationships. However, traditional hierarchical clustering methods always return a hierarchy, even when the data contain no meaningful hierarchical structure. Moreover, agglomerative linkage algorithms are highly sensitive to the choice of linkage function. In this paper, we revisit a classical notion of well-separated clusters, which we call valid clusters. The collection of all valid clusters forms a hierarchy, known as the Apresjan hierarchy. This hierarchy is the finest hierarchy composed only of valid clusters: it need not be binary, and it collapses to a star tree when no nontrivial valid clusters exist. Our main contribution is to characterize when the Apresjan hierarchy can be recovered from linkage-based algorithms. We propose a two-step procedure that first constructs a binary hierarchy using an agglomerative linkage method and then prunes all clusters that violate the validity condition. We give necessary and sufficient conditions on the linkage function under which this procedure exactly recovers the Apresjan hierarchy. Consequently, all linkage rules satisfying these conditions yield the same pruned hierarchy. In particular, single, complete, and average linkage satisfy the conditions, whereas Ward's linkage does not.

NeurIPS 2026

Recovering Evolving User Preference State via Adaptive Interaction-aware Representation Correction

Parthiv Chatterjee, Dhiraj Golhar, Ummesalma Diwan, Sourish Dasgupta, Manjunath Joshi, Tanmoy Chakraborty

Personalization systems encode long-horizon, evolving user trajectories into compressed preference states that downstream task heads consume for prediction or generation. This compression is difficult because preference trajectories contain stable long-term interests, transient short-term shifts, and episodic bursty interests. We argue that a practical route is not to design another task-specific encoder or incur costly host-encoder finetuning, but to correct the under-expressed compressed state before the downstream task head consumes it. We propose $\texttt{REPAIR}$ as a selective *pre-head state-repair method* for frozen personalization encoders. It plugs into frozen hosts, uses event representations from the forward pass, and avoids a second pass over the raw history. $\texttt{REPAIR}$ compares the compressed state with per-timestep event representations, estimates state-relative corrective evidence, resolves it through long-term, short-term, and episodic temporal regimes, and retains only the most corrective signals to form a compact correction. We evaluate $\texttt{REPAIR}$ across recommendation and generation personalization settings using MovieLens, MIND, PENS, and Amazon Reviews 2023. Across recommendation tasks, $\texttt{REPAIR}$ improves the evaluated frozen hosts. On MovieLens, it improves the highest-scoring frozen host in our instantiated baseline suite by +1.27/+1.54 MRR/nDCG@5; on MIND, it improves the highest-scoring frozen host by +4.41 MRR; and on Amazon product recommendation, it improves two SOTA baselines by +15.33 and +17.91 MRR. It also outperforms budget-matched post-head correctors, and the full long-, short-, and episodic repair remains the strongest temporal variant. On PENS personalized headline generation, $\texttt{REPAIR}$ improves subjectivity-sensitive generation most when the decoder is preference-coupled, with average PerSEval gains of +14.62% and +22.19% for two representative preference-coupled decoders. Relative to frozen predictive encoders, deployment overhead is 31--34% memory and 38--44% latency.

NeurIPS 2026

Recovering Clean Evaluation Metrics from Contaminated Benchmarks

Míriam Barrabés, Daniel Mas Montserrat, Maria Perera, Alexander Ioannidis

When benchmark examples overlap with a model’s training data, benchmark contamination can substantially inflate reported evaluation metrics, yet training provenance is often unavailable. We study post-hoc recovery of uncontaminated evaluation metrics in supervised tabular classification and regression using only prediction–label pairs from a potentially contaminated benchmark. We introduce MILAN (Metric Integrity via Leakage-Aware Normalization), a meta-trained framework that models a contaminated benchmark as a mixture of training-origin and clean evaluation examples and estimates soft posterior weights for the clean component to correct evaluation metrics. MILAN supports a broad class of metrics through weighted estimators and metric-specific correction procedures, and can optionally incorporate contamination-rate priors and sample-wise difficulty scores. To quantify uncertainty, MILAN additionally provides split-conformal prediction intervals with marginal coverage across exchangeable recovery problems. Across a large suite of simulated recovery problems with held-out datasets and model families, MILAN consistently improves clean-metric recovery over thresholding, clustering, mixture-model, anomaly-detection, and membership-inference baselines. In a polygenic risk score case study using UK Biobank evaluation data, MILAN improves agreement with independent FinnGen reference metrics. We provide a scikit-learn-style implementation at \url{hidden-for-submission}.

NeurIPS 2026

RecoverBench: A Systematic Benchmark for Error Recovery in Robotic Manipulation

Zijia Tang, Ganlong Zhao, Xingping Chen, Junye Chen, Zihao Mo, Zedi Wang, Guanbin Li

Robotic manipulation policies have achieved remarkable success in controlled settings, but they catastrophically fail when execution errors occur---dropped objects, collisions, misaligned grasps. Despite the critical importance of error recovery for real-world deployment, no existing benchmark systematically evaluates manipulation policies' ability to recover from such errors. We introduce RecoverBench, the first systematic benchmark for error recovery in robotic manipulation. We propose a taxonomy of 12 Error Skills organized into 5 Recovery Behavior Groups (RBGs), spanning 24 error subtypes across 2 difficulty degrees. Our Error Skill pipeline automatically generates 1,360 reproducible error scenes from clean demonstration trajectories across 6 manipulation tasks. Each error scene includes complete simulation state snapshots, environment fingerprints, and RNG states for deterministic reproduction. Beyond evaluation, RecoverBench also supports recovery-demo collection and augmentation, and we show that this recovery supervision improves recovery performance. We evaluate 4 representative manipulation policies on RecoverBench. Even the best-performing policy reaches only 48.6% average recovery success, ranging from 32.0% on threading to 76.7% on stack, showing that current methods still lack robust recovery. These results highlight the need for dedicated recovery evaluation and position RecoverBench as a benchmark for improving recovery robustness in manipulation policies. Code, data, and evaluation protocols will be released.

NeurIPS 2026

Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models

Nilaksh, Saurav Jha, Artem Zholus, Sarath Chandar

World model-based policy evaluation is a practical proxy for testing real-world robot control by rolling out candidate actions in action-conditioned video diffusion models. As these models increasingly adopt latent diffusion modeling (LDM), choosing the *right latent space* becomes critical. While the status quo uses autoencoding latent spaces like VAEs that are primarily trained for pixel *reconstruction*, recent work suggests benefits from pretrained encoders with representation-aligned *semantic* latent spaces. We systematically evaluate these latent spaces for action-conditioned LDM by comparing six reconstruction and semantic encoders to train world model variants under a fixed protocol on BridgeV2 dataset, and show effective world model training in high-dimensional representation spaces with and without dimension compression. We then propose three axes to assess robotic world model performance: visual fidelity, planning and downstream policy performance, and latent representation quality. Our results show visual fidelity alone is insufficient for world model selection. While reconstruction encoders like VAE and Cosmos achieve strong pixel-level scores, semantic encoders such as V-JEPA 2.1 (strongest overall on policy), Web-DINO, and SigLIP 2 generally excel across the other two axes at all model scales. Our study advocates semantic latent space as stronger foundation for policy-relevant robotics diffusion world models.

NeurIPS 2026

Reconstructing the Vocal Tract with Differentiable Acoustic Simulation

Eric Chen, Jin Woo Lee, Vincent Sitzmann

The human vocal tract, the cavity consisting of one's throat, mouth, lips opening, etc., filters one's voice to create the sounds we know as speech. In this paper, we present a differentiable and GPU parallelizable acoustic simulator that synthesizes speech by propagating sound along an acoustic tube representation of the vocal tract, and via its gradients, solves the inverse problem: reconstructing the geometry of their vocal tract solely from the sound it produces. Although learning the inverse mapping between geometry and sound is notoriously non-convex, we discover that gradient descent succeeds with three technical contributions: (1) we design a frequency domain formulation of the vocal tract's fluid dynamics that is 70x more GPU parallelizable than finite differences in time, (2) we integrate a differentiable model for turbulence to synthesize consonants, and (3) similar to prior work in implicit neural representations (INRs) and neural radiance fields (NeRFs), we find that parameterizing the geometry with a neural network accelerates convergence and escapes local minima that trap discrete representations. Because the simulator is differentiable, it is readily integrated with other deep learning pipelines to enable novel speech and medical imaging applications. Our model can be used for instance, in singing instruction or language learning, where a visualization of one's vocal tract can help people understand how their vocal tract maps to different speech sounds. To enable these tasks, (1) we demonstrate self-supervised autoencoding of vocal tract shapes across 11 languages, and (2) we couple our simulator with a generative model of MRI images to reconstruct one's moving vocal tract from only their speech, no paired data required.

NeurIPS 2026

Reconsidering Positional Supervision in Masked Diffusion Language Model Training

Mengyu Ye, Keito Kudo, Ryosuke Takahashi, Jun Suzuki

Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models. They can be viewed as parallel decoders trained with a position-wise cross-entropy (CE) loss, the same setup as non-autoregressive translation (NAT). In NAT, CE-trained parallel decoders have been argued to be sensitive to small positional shifts, since CE penalizes them harshly. We ask whether CE-trained MDLMs are similarly sensitive to such shifts under iterative decoding. To probe this, we apply a controlled intervention that introduces them during decoding. On LLaDA-8B-Instruct with Arena-Hard, displacing as little as 1\% of generated tokens by one position substantially reduces win rates against the unintervened model, showing that MDLMs are sensitive to such small shifts under iterative parallel decoding. Motivated by this, we adapt connectionist temporal classification (CTC), an alignment-flexible objective known to mitigate it there, to MDLM supervised fine-tuning. By relaxing the strict position-wise match that CE imposes, CTC gives the loss room to absorb small positional shifts; concretely, we modified CTC objective to use a special \ token that absorbs positional uncertainty between target tokens and output positions, and a updated collapse map that preserves target surface forms. Across four open-ended generation benchmarks, the resulting model consistently improves over both the original model and a matched cross-entropy-trained baseline, with statistically significant gains on all four. These results identify training-side alignment flexibility as a useful design dimension for MDLM SFT, complementary to the inference-time approaches explored in prior work.

NeurIPS 2026

Reconfiguring Procedural Knowledge for Compositional Robot Skill Adaptation

Daehee Lee, Dongsu Lee, Sanghyun Ahn, Minjong Yoo, Honguk Woo

General-purpose behavior models increasingly internalize broad procedural knowledge at training time, making adaptation less a problem of learning entirely new behaviors than of reconfiguring existing competence for new goals, object relations, and skill interfaces. We study this as reconfigurability, the ability to realize new behaviors by restructuring components and relations cost-efficiently, under *sparse governing information*, where a task specification provides high-level goals or abstract directives but omits the concrete bindings and compositions required for execution. We propose RecPo, a framework that represents skills task-agnostically through multiple procedure views and materializes a new task by composing only the transition relations consistent with the task-relevant views. RecPo maintains a procedure knowledge base of local transition relations within each view. At deployment time, it interprets a task demonstration through the same views, converts observed view-level changes into a compositional query, and resolves the query into an executable skill sequence. On an extended Franka Kitchen benchmark with held-out long-horizon tasks outside the stored compositions, RecPo achieves 91.7\% ordered subtask completion, substantially outperforming non-reconfigurable skill retrieval baselines. Real-robot case studies further show deployment-time adaptation through recomposition rather than task-specific retraining.

NeurIPS 2026

Reconciling Safety and Performance via Dual-Expert Offline Imitation Learning

Seokin Seo, Sung Kuk Shyn, Minji Seo, Yisoo Lee, Jongmin Lee, Hongseok Yang, Kee-Eung Kim

Ensuring high returns while providing strong safety guarantees in offline imitation learning (IL) is a fundamental challenge: existing approaches either rely on explicitly specified cost functions, which are difficult to design for complex real-world safety constraints, or require expert demonstrations that are both safe and high-performing, which are often too costly to collect. We introduce *dual-expert imitation learning*, which leverages two complementary data sources: (i) safety-compliant demonstrations that faithfully follow safety guidelines but may be suboptimal, and (ii) performance-oriented demonstrations that achieve high returns but may violate safety guidelines. To address this problem, we propose DexDICE (**D**ual-**ex**pert offline imitation learning via stationary **DI**stribution **C**orrection **E**stimation). Instead of conventional distribution constraints, DexDICE combines DICE-style offline learning with safe support constraints, enabling agents to exploit high-return behaviors while remaining within safety-compliant regions. We evaluate DexDICE on a re-curated DSRL benchmark and validate it on a real-world mobile-robot navigation task trained directly from human teleoperation demonstrations, where it significantly outperforms offline IL baselines and remains robust to data scarcity and quality degradation.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.