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.

ICML 2026

Learning Manifold and Itô Dynamics with Branched Neural Rough Differential Equations

Luke Thompson, Dai Shi, Lequan Lin, Junbin Gao, Andi Han

Neural rough differential equations (NRDEs) stay accurate under irregular sampling while taking far fewer integration steps than standard neural differential equations, summarising a finely sampled driver by its log-signature and advancing the hidden state over coarse intervals using the log-ODE method. This efficiency rests on the shuffle algebra, the algebraic counterpart of Stratonovich calculus. This reliance means NRDEs cannot expose the quadratic-variation terms Itô dynamics require, nor the ordered covariant derivatives that govern Itô flows on connection-equipped manifolds. Ameliorating this, we introduce Branched Neural Rough Differential Equations (B-NRDEs), a Hopf-algebraic framework that recasts the NRDE log-ODE step as geometric numerical integration on the state-space manifold, matching the driving algebra to the governing calculus: Grossman–Larson rooted trees for Euclidean Itô dynamics, Munthe–Kaas–Wright planar rooted trees for ordered covariant derivatives on manifolds, and the shuffle algebra in the classical Stratonovich case. This yields intrinsic coarse-step dynamics that exactly preserve manifold constraints. Finally, we introduce a branched signature-kernel objective to enable Itô-consistent law matching by making quadratic-variation terms visible during training. On rough Bergomi volatility, sim-to-real $\mathrm{SO}(3)$ forecasting, and SPD covariance dynamics, B-NRDEs offer a unified, effective approach to stochastic and manifold-valued dynamics beyond the Euclidean–Stratonovich setting.

ICML 2026

FedCDWA: Decoupled Federated Prototype Distillation with Hierarchical Wasserstein Aggregation

Zhenshen Liu, Kai Fan, Wenjie Li, Kuan Zhang, Hui Li, Yintang Yang

Federated learning enables decentralized clients to collaboratively train models without sharing local data. However, heterogeneous client distributions often induce client drift and hinder convergence. This paper proposes FedCDWA, a decoupled hierarchical federated distillation framework. FedCDWA decouples client-side personalized distillation from server-side mutual distillation to mitigate distillation-induced optimization conflicts. It further adopts Hierarchical Wasserstein Aggregation to aggregate prototypes without restrictive parametric assumptions while preserving intra-class structure and inter-class geometry. To achieve finer-grained feature alignment, Prototype–Variance Dual Alignment matches feature means and variances in the feature space. We prove convergence guarantees for FedCDWA. Experiments on three datasets demonstrate that FedCDWA consistently improves both global and personalized accuracy across heterogeneity levels, with smaller performance degradation under more severe heterogeneity.

ICML 2026

Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch

Hyunwoo Kim, Niloofar Mireshghallah, Michael Duan, Rui Xin, Shuyue Stella Li, Jaehun Jung, David Acuna, Qi Pang, Hanshen Xiao, G. Edward Suh, Sewoong Oh, Yulia Tsvetkov, Pang Wei Koh, Yejin Choi

Research involving privacy-sensitive data has always been constrained by data scarcity, standing in sharp contrast to other areas that have benefited from data scaling. To quench this thirst, we present Privasis (i.e., privacy oasis), the first million-scale fully synthetic dataset entirely built from scratch—an expansive reservoir of texts with rich and diverse private information—designed to broaden and accelerate research in areas where processing sensitive social data is inevitable. Compared to existing datasets, Privasis, comprising 1.4 million records, offers orders-of-magnitude larger scale with quality, and far greater diversity across various document types, including medical records, legal documents, financial records, calendars, emails, meeting transcripts, and text-messages with a total of 55.1 million annotated attributes such as ethnicity, date of birth, workplace, etc. We leverage Privasis to construct a parallel corpus for text sanitization with our pipeline that recursively decomposes texts and applies targeted sanitization. Our compact sanitization models ($\leq$ 4B) trained on this dataset outperform state-of-the-art large language models, such as GPT-5 and Qwen-3 235B.

ICML 2026

EmWorld: Emotion World Model with Latent State Evolution for Scenario-Incremental Dynamic Facial Expression Recognition

Ke Wang, Yuanyuan Liu, Kejun Liu, Yuyang Xia, Chang Tang, Yibing Zhan, Zhe Chen

Dynamic Facial Expression Recognition (DFER) models the temporal evolution of facial expressions in videos. In real-world scenarios, changing scenarios distort expression trajectories, challenging existing methods. Most current approaches address this via passive feature alignment or domain-incremental learning but do not explicitly model scenario evolution, limiting their ability to capture expression dynamics under scenario-incremental changes. To address this, we propose **EmWorld**, an emotion world model for DFER that explicitly models latent emotion state evolution under scenario variations. Specifically, **EmWorld** formulates scenario-incremental DFER as a progressive Bayesian inference problem over latent world states with dual temporal scales. Slow-timescale component (**STS**) models scenario evolution using stochastic evolutionary priors, capturing long-term scenario effects and providing proactive guidance in new scenarios. Fast-timescale component (**FTS**) models frame-level expression dynamics with temporally consistent latent transitions, decoupling expression dynamics from scenario influences. By jointly inferring latent states at both timescales, EmWorld shifts DFER from a passive feature discrimination to active probabilistic state inference under evolving scenarios. Experiments on FERV39k, DFEW, and MAFW demonstrate that EmWorld consistently outperforms state-of-the-art methods, achieving up to 3.84\% improvement while exhibiting strong cross-scenario stability and long-term robustness.

ICML 2026

The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

Donghang Wu, Tianyu Zhang, Yuxin Li, Hexin Liu, Chen Chen, Eng Siong Chng, Yoshua Bengio

During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental in formulating high-quality responses. Inspired by this cognitive phenomenon, we propose a novel **F**ull-duplex **LA**tent and **I**nternal **R**easoning method named FLAIR that conducts *latent* thinking simultaneously with speech perception. Unlike conventional "thinking" mechanisms in NLP, which require post-hoc generation, our approach aligns seamlessly with spoken dialogue systems: during the user’s speaking phase, it recursively feeds the latent embedding output from the previous step into the next step, enabling continuous reasoning that strictly adheres to causality without introducing additional latency. To enable this latent reasoning, we design an Evidence Lower Bound-based objective that supports efficient supervised finetuning via teacher forcing, circumventing the need for explicit reasoning annotations. Experiments demonstrate the effectiveness of this think-while-listening design, which achieves competitive results on a range of speech benchmarks. Furthermore, FLAIR robustly handles conversational dynamics and attains competitive performance on full-duplex interaction metrics.

ICML 2026

Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization

Jinghan Li, Junfeng Fang, Jinda Lu, Yuan Wang, Xiaoyan Guo, Tianyu Zhang, Xiang Wang, Xiangnan He

Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these methods to multimodal settings, however, faces a critical challenge: the instability of std-based normalization, which is easily distorted by extreme samples with nearly positive or negative rewards. Unlike pure-text LLMs, multimodal models are particularly sensitive to such distortions, as both perceptual and reasoning errors influence their responses. To address this, we characterize each sample by its difficulty, defined through perceptual complexity (measured via visual entropy) and reasoning uncertainty (captured by model confidence). Building on this characterization, we propose difficulty-aware group normalization (Durian), which re-groups samples by difficulty levels and shares the std within each group. Our approach preserves GRPO's intra-group distinctions while eliminating sensitivity to extreme cases, yielding significant performance gains across multiple multimodal reasoning benchmarks.

ICML 2026

Robust Self-reflective Hashing for Cross-modal Retrieval with Noisy Label

Hao Sun, Qibing Qin, Lei Huang

Cross-modal Hashing (CMH) typically assumes a perfectly complete data annotation, whereas noisy labels are unavoidable in practical scenarios. Existing CMH methods often overlook the uncertainty introduced by noise or semantic ambiguity, making models susceptible to overfitting noisy labels and yielding unreliable similarity judgments during inference. To address this issue, we propose a Robust Self-reflective Hashing (RSH) framework that prudently analyzes semantic discrepancies while accounting for uncertainty, thereby effectively mitigating interference from noisy labels. Specifically, the Double Feature Representation (DFR) method is introduced, employing semantic and uncertainty features to represent the semantic representation and fuzziness of samples. With a double feature, we propose a novel cross-modal similarity metric - the Self-reflective Similarity Metric (SSM), which judges sample similarity by integrating semantic discrepancy and fuzziness, enabling the model to adaptively weaken semantic discrepancy according to uncertainty level. The proposed method is plug-and-play, enabling seamless integration into diverse objective functions to enhance model robustness and reliability. Extensive experiments on benchmark datasets demonstrate that RSH outperforms existing methods. Code is available at https://github.com/QinLab-WFU/RSH.

ICML 2026

Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment

Mathieu Petitbois, Rémy Portelas, Sylvain Lamprier

We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to distribution shift and inherent conflicts between style and reward. Existing methods, despite introducing numerous definitions of style, often fail to reconcile these objectives effectively. To address these challenges, we propose a unified definition of behavior style and instantiate it into a practical framework. Building on this, we introduce Style-Conditioned Implicit Q-Learning (SCIQL), which leverages offline goal-conditioned RL techniques, such as hindsight relabeling and value learning, and combine it with a new Gated Advantage Weighted Regression mechanism to efficiently optimize task performance while preserving style alignment. Experiments demonstrate that SCIQL achieves superior performance on both objectives compared to prior offline methods. Code, datasets and visuals are available in: https://mathieu-petitbois.github.io/projects/sciql/.

ICML 2026

CrossQ: Task-Aligned Cross-Token Conditional Quantization for Late Interaction Retrieval

Rohit Kumar Salla, Manoj Saravanan, Ramya Manasa Amancherla

Late-interaction retrievers like ColBERT achieve high quality but suffer from large multi-vector indices. Standard compression minimizes token reconstruction error, while ranking depends critically on preserving scores of sparse "winner" tokens. We introduce CrossQ, which adaptively improves effective token fidelity within documents by conditioning token codes on lightweight document context computed at indexing time (but not stored). CrossQ is trained with ranking-aligned objectives that preserve candidate score distributions and protect hard-negative margins. At 2 B/token, CrossQ improves MRR@10 by +0.010 over the strongest strictly footprint-matched quantization baseline and by +0.012 over the strongest candidate-matched system reference. On the nine-dataset BEIR subset reported in Appendix G.1, CrossQ improves average nDCG@10 by +0.009 at 4 B/token over the strongest candidate-matched system reference. At 4 B/token, CrossQ achieves $64\times$ raw token-storage reduction, approximately $61\times$ including metadata and approximately $58\times$ under conservative padding/alignment accounting. At 8 B/token, CrossQ + light fine-tuning retains approximately 98% of full-precision ColBERT MRR@10, improving the footprint-quality tradeoff for memory-constrained late-interaction retrieval.

ICML 2026

Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification

Wujian Peng, Lingchen Meng, Yuxuan Cai, Xianwei Zhuang, Yuhuan Yang, Rongyao Fang, Chenfei Wu, Junyang Lin, Zuxuan Wu, Shuai Bai

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation space and hinders truly unified modeling. We propose UniAR, a unified autoregressive framework where a single discrete visual tokenizer serves as the key bridge between understanding and generation, enabling a shared context in which the model can directly interpret its own generated visual tokens without additional re-encoding. UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme, preserving both high-level semantics and low-level details while scaling the effective visual vocabulary at minimal cost. Building on this, the unified autoregressive model adopts parallel-bitwise-prediction to jointly predict spatially grouped, multi-level visual codes, substantially reducing visual sequence length and accelerating generation. Finally, a diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images. Through large-scale pre-training, followed by supervised fine-tuning and reinforcement learning, UniAR achieves state-of-the-art performance on image generation and image editing while remaining competitive on multimodal understanding benchmarks. The project homepage is at https://sharelab-sii.github.io/uniar-web.

ICML 2026

Temporal Difference Learning for Diffusion Models

Qizhen Ying, Yangchen Pan, Victor Adrian Prisacariu, Junfeng Wen

Diffusion models are typically trained with objectives that focus on local denoising targets at individual time steps (or adjacent pairs), which do not enforce consistency between predictions along the denoising trajectory. This lack of cross-time consistency can degrade performance, especially for few-step samplers. We introduce a temporal difference (TD) objective that penalizes inconsistency of the model’s \emph{multi-step} progress along the denoising path. By reformulating the diffusion process as a Markov reward process and casting denoising as a policy evaluation problem in reinforcement learning, we derive a unified TD approach that applies to both discrete- and continuous-time diffusion formulations. We further propose a principled sample-based reweighting method that stabilizes training. Empirically, we show that using our TD training can significantly improve sample quality measured by FID, with stronger advantages when the number of sampling steps is small, highlighting its practical utility under low-computation-budget scenarios. We provide ablation studies to justify our design choices, including pairwise loss reweighting, regularization weight, and one-step stride. Overall, our TD approach can be a general drop-in that enforces cross-time consistency and improves generation quality across different diffusion generative models.

ICML 2026

A Graph Foundation Model with Cross-Modal Alignment and Modality-Aware Expert Fusion for Multi-Modal Graphs

Dongxiao He, Ankang Yang, Jitao Zhao, Di Jin

Graph Foundation Models (GFMs) aim to learn universal patterns through large-scale pretraining on diverse graphs and generalize to open-world scenarios. While GFMs have garnered significant attention, existing works primarily focus on sigle-modal graphs. However, many real-world graphs are multimodal, consisting of structures alongside diverse features derived from modalities such as text and images. To date, exploration into Multimodal Graph Foundation Models (MGFMs) remains limited. Incorporating multimodal data provides a more comprehensive view, allowing models to learn richer semantics, thereby advancing GFMs. We are therefore motivated to explore MGFMs, where the core challenge lies in synergistically encoding structures and multimodal features to achieve effective cross-modal alignment and fusion. To this end, we propose a graph foundation model with Cross-modal Alignment and Modality-aware Expert fusion, CAME. Specifically, CAME first generates graph embeddings for each individual modality. We then introduce a multimodal multi-expert encoding mechanism, which includes a dimension-wise routing strategy to fuse multimodal information. Finally, we employ a cross-modal contrastive loss to train CAME, enabling the adaptive alignment and fusion across different modalities. Extensive experiments demonstrate the effectiveness of CAME across multiple tasks and diverse multimodal graph datasets.

ICML 2026

Language Generation with Feedback: Queries and Mistakes

Steve Hanneke, amin karbasi, Anay Mehrotra, Grigoris Velegkas

We investigate language generation in the limit (Kleinberg & Mullainathan, 2024; Li et al., 2025) in variants where the generator receives some feedback based on its “actions.” We study two such variants. In the first, which is inspired by Littlestone’s model of online learning, the generator observes whether it made a mistake at each iteration. In the second, introduced by Charikar & Pabbaraju (2025a), the generator can query whether a string belongs to the target language. Our main result is a characterization of collections that are generable with mistake feedback. Using similar techniques, we also characterize when generation is possible in the query model with set-based generators; set-based generators have been studied in several works (Charikar & Pabbaraju, 2025a; Kalavasis et al., 2025; Kleinberg & Wei, 2025a; Li et al., 2025). Beyond the characterizations themselves, we derive several implications. First, our results imply new closure properties for generation with mistake and query feedback. Second, our results show that, under feedback, generation is robust to noise: it remains possible with arbitrary contamination in the adversary’s examples and with finite contamination in the feedback. Third, our techniques also yield new sufficient and necessary conditions for generation without feedback among other implications.

ICML 2026

OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

Zhihong Chen, Xuehai Bai, Yang Shi, Chaoyou Fu, Huanyu Zhang, Haotian Wang, Xiaoyan Sun, Zhang Zhang, Liang Wang, Yuanxing Zhang, Pengfei Wan, Yifan Zhang, Yi-Fan Zhang

The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and simple object manipulation, they often lack the systematic structure and challenging scenarios required for real-world applications. To address this bottleneck, we introduce OpenGPT-4o-Image, a large-scale dataset constructed using a novel methodology that combines hierarchical task taxonomy with automated data generation. Our taxonomy not only includes fundamental capabilities such as text rendering and style control but also introduces highly practical yet challenging categories like scientific imagery for physics/chemistry illustrations and complex instruction editing requiring simultaneous execution of multiple operations. Through an automated pipeline leveraging structured resource pools and GPT-4o, we generate 80k high-quality instruction-image pairs with controlled diversity, covering 11 major domains and 51 subtasks. Extensive experiments show that fine-tuning leading models on our dataset achieves significant performance gains across multiple benchmarks, with improvements of up to 18% on editing tasks UniWorld-V1 on ImgEdit-Bench and 13% on generation tasks Harmon on GenEval. Our work demonstrates that systematic data construction is key to advancing multimodal AI capabilities.

ICML 2026

Video-SVD: Efficient Video Diffusion via Orthogonal Basis Composition

Zhang Wan, Yu Li, Tianze Huang, Haochen Li, Juan Cao, Sheng Tang

Video Diffusion Transformers (VDiTs) represent the state of the art in video generation but remain constrained by the quadratic complexity of dense self-attention. To address this attention bottleneck, we analyze the pre-softmax matrix ($QK^\top$) and reveal two key properties: (1) video attention exhibits an effective low-dimensional structure with rapid singular-value decay, and (2) real motion induces hybrid spatio-temporal patterns rather than rigid ``spatial vs. temporal'' layouts. Guided by these observations, we propose Video-SVD, a training-free and plug-and-play acceleration method that does not modify the original network parameters. Video-SVD learns checkpoint-adaptive orthogonal bases offline and, at inference time, replaces expensive dense attention computation with lightweight online subspace projection and basis composition. To preserve high fidelity, Video-SVD further employs layer-shared dual-stream residual modules to recover fine-grained content details and positional information. Across HunyuanVideo and Wan2.1 backbones, Video-SVD achieves significant end-to-end speedups while maintaining high visual quality, reaching 1.92$\times$ on HunyuanVideo, 1.75$\times$ on Wan2.1-1.3B, and 1.79$\times$ on Wan2.1-14B.

ICML 2026

Doubly Robust Distributionally Robust Offline Contextual Pricing

Min Xu, Xinyi Yin, Yunfan Zhang, Yuxuan Han, Houcai Shen, Caihua Chen

Offline contextual pricing often relies on logged observational data, but faces challenges from distributional shifts between training and deployment environments. Distributionally robust optimization (DRO) provides a principled approach to off-policy evaluation and learning (OPE/L). However, existing methods are mostly limited to discrete actions. Recent work has explored DRO for continuous treatments using inverse propensity weighting (IPW), while such IPW-based estimators can be sensitive to the convergence rate of propensity score estimates, particularly when estimated nonparametrically, which may lead to larger estimation errors and regret. In this work, we develop a doubly robust (DR) framework for distributionally robust OPE/L in continuous pricing settings. For evaluation, we propose a localized DR estimator that addresses the computational challenges of worst-case expectations by fitting only a small number of regressions, comparable to standard non-robust DR, while achieving semiparametric efficiency under mild product rate conditions. For learning, we leverage the inherent smoothness of demand noise to handle pricing-specific discontinuities in revenue outcomes (e.g., threshold-based purchase decisions), establishing a finite-sample regret bound of $\tilde{\mathcal{O}}_p(T^{-s/(2s+1)})$ for smoothness orders $s=1,2$. This bound improves upon existing regret rates in existing DRO-based off-policy learning (OPL) for continuous treatments. Extensive experiments under various levels of distribution shift validate our proposed framework.

ICML 2026

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning

Nicolas Anguita, Francesco Locatello, Andrew M Saxe, Marco Mondelli, Flavia Mancini, Samuel Lippl, Clémentine Carla Juliette Dominé

Pretraining and fine-tuning are central stages in modern machine learning systems. In practice, feature learning plays an important role across both stages: deep neural networks learn a broad range of useful features during pretraining and further refine those features during fine-tuning. However, an end-to-end theoretical understanding of how choices of initialization impact the ability to reuse and refine features during fine-tuning has remained elusive. Here we develop an analytical theory of the pretraining–fine-tuning pipeline in diagonal linear networks, deriving exact expressions for the generalization error as a function of initialization parameters and task statistics. We find that different initialization choices place the network into four distinct fine-tuning regimes that are distinguished by their ability to support feature learning and reuse—and therefore by the task statistics for which they are beneficial. In particular, a smaller initialization scale in earlier layers enables the network to both reuse and refine its features, leading to superior generalization on fine-tuning tasks that rely on a subset of pretraining features. We demonstrate empirically that the same initialization parameters impact generalization in ResNets trained on CIFAR-100 and SVHN as well as Transformers trained on modular arithmetic tasks. Overall, our results demonstrate analytically how data and network initialization interact to shape fine-tuning generalization, highlighting an important role for the relative scale of initialization across different layers in enabling continued feature learning during fine-tuning.

ICML 2026

Safeguarded Stochastic Polyak Step Sizes for Non-smooth Optimization: Robust Performance Without Small (Sub)Gradients

Dimitris Oikonomou, Nicolas Loizou

The stochastic Polyak step size (SPS) has proven to be a promising choice for stochastic gradient descent (SGD), delivering competitive performance relative to state-of-the-art methods on smooth convex and non-convex optimization problems, including deep neural network training. However, extensions of this approach to non-smooth settings remain in their early stages, often relying on interpolation assumptions or requiring knowledge of the optimal solution. In this work, we propose a novel SPS variant, Safeguarded SPS (SPS$_{safe}$), for the stochastic subgradient method, and provide rigorous convergence guarantees for non-smooth convex optimization with no need for strong assumptions. We further incorporate momentum into the update rule, yielding equally tight theoretical results. Comprehensive experiments on convex benchmarks and deep neural networks corroborate our theory: the proposed step size achieves competitive performance to existing adaptive baselines and exhibits stable behavior across a wide range of problem settings. Finally, in the context of deep neural network training, the gradient norms under our step size do not collapse to (near) zero, indicating robustness to vanishing gradients.

ICML 2026

Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search

Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis

Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing approaches frequently depend on curated prompt datasets - either manually constructed or generated with large language models (LLMs) - as part of their training and/or evaluation procedures. Beside the curation cost, this also risks overlooking unanticipated, less obvious prompts that trigger biased generation, even in models that have undergone debiasing. In this work, we introduce Bias-Guided Prompt Search (BGPS), a framework that automatically generates prompts that aim to maximize the presence of biases in the resulting images. BGPS comprises two components: (1) an LLM instructed to produce attribute-neutral prompts and (2) attribute classifiers acting on the TTI’s internal representations that steer the decoding process of the LLM toward regions of the prompt space that amplify the image attributes of interest. We conduct extensive experiments on Stable Diffusion 1.5 and a state-of-the-art debiased model and discover an array of subtle and previously undocumented biases that severely deteriorate fairness metrics. Crucially, the discovered prompts are interpretable, i.e they may be entered by a typical user, quantitatively improving the perplexity metric compared to a prominent hard prompt optimization counterpart. Our findings uncover TTI vulnerabilities, while BGPS expands the bias search space and can act as a new evaluation tool for bias mitigation.

ICML 2026

Decision Transformers As Zero-Shot Learners via Text-Behavior Alignment

Xin Zhang, Jonathan Martinez, Yanhua Li, Yingxue Zhang

Offline meta-reinforcement learning (meta-RL) aims to train agents that can generalize to unseen tasks using pre-collected data from related tasks. Recent approaches leverage the scalability of transformer architectures to model behavior sequences and support task adaptation using target task demonstrations. However, such data is often unavailable in real-world settings, where the task objective may be known but cannot be easily demonstrated. In contrast, humans routinely interpret and perform new tasks based solely on natural language instructions. In this work, we explore the potential of using natural language task descriptions to enable zero-shot task adaptation in offline meta-RL without requiring any data from the target task. We propose the Text-Guided Decision Transformer (TG-DT), a framework that enables zero-shot generalization by grounding policy learning in natural language. TG-DT learns a shared embedding space between task descriptions and behavioral trajectories via a dual contrastive and matching-based objective, ensuring robust alignment. A transformer-based policy is then conditioned on these aligned representations to generate task-appropriate actions. At test time, TG-DT synthesizes policies for unseen tasks using only their text descriptions and can optionally leverage a description-guided data sharing strategy to enhance adaptation. Experiments on standard offline meta-RL benchmarks, including MuJoCo and Meta-World, demonstrate that TG-DT achieves strong generalization to unseen tasks.

Keep browsing

More papers from top AI conferences

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