Reinforcement-learning agents often struggle when deployed from simulation to the real-world. A dominant strategy for reducing the sim-to-real gap is domain randomization (DR) which trains the policy across many simulators produced by sampling dynamics parameters, but standard DR ignores offline data already available from the real system. We study offline domain randomization (ODR), which first fits a distribution over simulator parameters to an offline dataset. While a growing body of empirical work reports substantial gains with algorithms such as DROPO, the theoretical foundations of ODR remain largely unexplored. In this work, we cast ODR as a maximum-likelihood estimation over a parametric simulator family and provide statistical guarantees: under mild regularity and identifiability conditions, the estimator is weakly consistent (it converges in probability to the true dynamics as data grows), and it becomes strongly consistent (i.e., it converges almost surely to the true dynamics) when an additional uniform Lipschitz continuity assumption holds. We examine the practicality of these assumptions and outline relaxations that justify ODR’s applicability across a broader range of settings. Taken together, our results place ODR on a principled footing and clarify when offline data can soundly guide the choice of a randomization distribution for downstream offline RL.
论文检索
输入标题、作者或关键词，从 12,113 篇学术成果中精准定位
General Machine Learning · Probabilistic Methods
We study density estimation from pairwise comparisons, motivated by expert knowledge elicitation and learning from human feedback. We relate the unobserved target density to a tempered winner density (marginal density of preferred choices), learning the winner's score via score-matching. This allows estimating the target by `de-tempering' the estimated winner density's score. We prove that the score vectors of the belief and the winner density are collinear, linked by a position-dependent tempering field. We give analytical formulas for this field and propose an estimator for it under the Bradley–Terry model. Using a diffusion model trained on tempered samples generated via score-scaled annealed Langevin dynamics, we can learn complex multivariate belief densities of simulated experts, from only hundreds to thousands of pairwise comparisons.
Reinforcement Learning · Everything Else
Verifiers provide important reward signals for reinforcement learning of large language models (LLMs). However, it is challenging to develop or create reliable verifiers, especially for code generation tasks. A well-disguised wrong solution program may only be detected by carefully human-written edge cases that are difficult to synthesize automatically. To address this issue, we propose HARDTESTGEN, an approach to synthesize high-quality test cases for algorithmic coding problems. We curate a comprehensive algorithmic programming dataset HARDTESTS with 26.6k problems and high-quality synthetic tests. Compared with existing tests, \method tests demonstrate significantly higher accuracy in verifying LLM-generated code (+11.22 percentage points in precision, the percentage of actually correct code within the predicted correct ones). We also show that downstream post-training --- including rejection sampling and reinforcement learning (RL) --- using HARDTESTS verifier results in improved performance of LLM code generation. We open-source our dataset and synthesis pipeline at https://leililab.github.io/HardTests/.
Computer Vision · 3D Rendering & Reconstruction
Modern camera pipelines apply extensive on-device processing, such as exposure adjustment, white balance, and color correction, which, while beneficial individually, often introduce photometric inconsistencies across views. These appearance variations violate multi-view consistency and degrade novel view synthesis. Joint optimization of scene-specific representations and per-image appearance embeddings has been proposed to address this issue, but with increased computational complexity and slower training. In this work, we propose a generalizable, feed-forward approach that predicts spatially adaptive bilateral grids to correct photometric variations in a multi-view consistent manner. Our model processes hundreds of frames in a single step, enabling efficient large-scale harmonization, and seamlessly integrates into downstream 3D reconstruction models, providing cross-scene generalization without requiring scene-specific retraining. To overcome the lack of paired data, we employ a hybrid self-supervised rendering loss leveraging 3D foundation models, improving generalization to real-world variations. Extensive experiments show that our approach outperforms or matches the reconstruction quality of existing scene-specific optimization methods with appearance modeling, without significantly affecting the training time of baseline 3D models.
Reinforcement Learning · Deep RL
Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific learning potential. In an effort to sample more efficiently, researchers introduced Prioritized Experience Replay (PER). In this paper, we propose an extension to PER by introducing a novel measure of temporal difference error reliability. We theoretically show that the resulting transition selection algorithm, Reliability-adjusted Prioritized Experience Replay (ReaPER), enables more efficient learning than PER. We further present empirical results showing that ReaPER outperforms both uniform experience replay and PER across a diverse set of traditional environments including several classic control environments and the Atari-10 benchmark, which approximates the median score across the Atari-57 benchmark within one percent of variance.
Probabilistic forecasting of multivariate time series is challenging due to non-stationarity, inter-variable dependencies, and distribution shifts. While recent diffusion and flow matching models have shown promise, they often ignore informative priors such as conditional means and covariances. In this work, we propose Conditionally Whitened Generative Models (CW-Gen), a framework that incorporates prior information through conditional whitening. Theoretically, we establish sufficient conditions under which replacing the traditional terminal distribution of diffusion models, namely the standard multivariate normal, with a multivariate normal distribution parameterized by estimators of the conditional mean and covariance improves sample quality. Guided by this analysis, we design a novel Joint Mean-Covariance Estimator (JMCE) that simultaneously learns the conditional mean and sliding-window covariance. Building on JMCE, we introduce Conditionally Whitened Diffusion Models (CW-Diff) and extend them to Conditionally Whitened Flow Matching (CW-Flow). Experiments on five real-world datasets with six state-of-the-art generative models demonstrate that CW-Gen consistently enhances predictive performance, capturing non-stationary dynamics and inter-variable correlations more effectively than prior-free approaches. Empirical results further demonstrate that CW-Gen can effectively mitigate the effects of distribution shift.
Deep Learning · Generative Models and Autoencoders
Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventional image tokenizations, which creates a fundamental misalignment with the unidirectional nature of autoregressive models. To resolve this, we introduce AliTok, a novel Aligned Tokenizer that alters the dependency structure of the token sequence. AliTok employs a bidirectional encoder constrained by a causal decoder, a design that compels the encoder to produce a token sequence with both semantic richness and forward-dependency. Furthermore, by incorporating prefix tokens and employing a two-stage tokenizer training process to enhance reconstruction performance, AliTok achieves high fidelity and predictability simultaneously. Building upon AliTok, a standard decoder-only autoregressive model with just 177M parameters achieves a gFID of 1.44 and an IS of 319.5 on ImageNet-256. Scaling to 662M, our model reaches a gFID of 1.28, surpassing the SOTA diffusion method with 10x faster sampling. On ImageNet-512, our 318M model also achieves a SOTA gFID of 1.39. Code and weights at https://github.com/ali-vilab/alitok.
Deep Learning · Generative Models and Autoencoders
The success of deep generative models in scientific discovery requires not only the ability to generate novel candidates but also reliable guarantees that these candidates indeed satisfy desired properties. Recent conformal-prediction methods offer a path to such guarantees, but its application to generative modeling in drug discovery is limited by budget constraints, lack of oracle access, and distribution shift. To this end, we introduce ConfHit, a distribution-free framework that provides validity guarantees under these conditions. ConfHit formalizes two central questions: (i) Certification: whether a generated batch can be guaranteed to contain at least one hit with a user-specified confidence level, and (ii) Design: whether the generation can be refined to a compact set without weakening this guarantee. ConfHit leverages weighted exchangeability between historical and generated samples to eliminate the need for an experimental oracle, constructs multiple-sample density-ratio weighted conformal p-value to quantify statistical confidence in hits, and proposes a nested testing procedure to certify and refine candidate sets of multiple generated samples while maintaining statistical guarantees. Across representative generative molecule design tasks and a broad range of methods, ConfHit consistently delivers valid coverage guarantees at multiple confidence levels while maintaining compact certified sets, establishing a principled and reliable framework for generative modeling.
Applications · Language, Speech and Dialog
Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time reward model (RM)-based reasoning as a critical yet overlooked avenue. In this paper, we conduct a systematic analysis of RM behavior across downstream reasoning tasks, revealing three key limitations: (1) RM can impair performance on simple questions, (2) its discriminative ability declines with increased sampling, and (3) high search diversity undermines RM performance. To address these issues, we propose CRISP (Clustered Reward Integration with Stepwise Prefixing), a novel inference-time algorithm that clusters generated reasoning paths by final answers, aggregates reward signals at the cluster level, and adaptively updates prefix prompts to guide generation. Experimental results demonstrate that CRISP significantly enhances LLM reasoning performance, achieving up to 5% accuracy improvement over other RM-based inference methods and an average of 10% gain over advanced reasoning models.
Theory · Interpretability and Visualization
While chain-of-thought prompting enables powerful multi-step reasoning in Large Language Models (LLMs), the stochastic nature of the generation process undermines its reliability. In this work, we first analyze thousands of reasoning paths to identify Reasoning Drift, a key failure mode where models get locked into flawed reasoning patterns. We reveal that the manifestation of drift is a complex interplay between universal functional tendencies and unique, model-specific signatures. Based on the diagnosis, we propose Reasoning-Aware Activation Steering, a novel inference-time intervention method to gently nudge the model's activations away from pathological patterns. We pre-compute a library of vectors from contrastive functional transitions and apply them dynamically. Experiments show that our method effectively mitigates the drift problem and boosts accuracy. Additionally, it generalizes to out-of-distribution tasks, demonstrating a deeper capture of valid reasoning principles.
Theory · Learning Theory
The recent empirical success of Mamba and other selective state space models (SSMs) has renewed interest in non-attention architectures for sequence modeling, yet their theoretical foundations remain underexplored. We present a first-step analysis of generalization and learning dynamics for a simplified but representative Mamba block: a single-layer, single-head selective SSM with input-dependent gating, followed by a two-layer MLP trained via gradient descent (GD). Our study adopts a structured data model with tokens that include both class-relevant and class-irrelevant patterns under token-level noise and examines two canonical regimes: majority-voting and locality-structured data sequences. We prove that the model achieves guaranteed generalization by establishing non-asymptotic sample complexity and convergence rate bounds, which improve as the effective signal increases and the noise decreases. Furthermore, we show that the gating vector aligns with class-relevant features while ignoring irrelevant ones, thereby formalizing a feature-selection role similar to attention but realized through selective recurrence. Numerical experiments on synthetic data justify our theoretical results. Overall, our results provide principled insight into when and why Mamba-style selective SSMs learn efficiently, offering a theoretical counterpoint to Transformer-centric explanations.
Applications · Neuroscience, Cognitive Science
Transformers form the foundation of modern generative AI, yet their key–value memory lacks inherent spatial priors, constraining their capacity for spatial reasoning. In contrast, neuroscience points to the hippocampal–entorhinal system, where the medial entorhinal cortex provides structural codes and the hippocampus binds them with sensory codes to enable flexible spatial inference. However, existing hippocampus models such as the Tolman-Eichenbaum Machine (TEM) suffer from inefficiencies due to outer-product operations or context-length bottlenecks in self-attention, limiting their scalability and integration into modern deep learning frameworks. To bridge this gap, we propose mm-TEM, an efficient and scalable structural spatial memory model that leverages meta-MLP relational memory to improve training efficiency, form grid-like representations, and reveal an intriguing link between prediction horizon and grid scales. Extensive evaluation shows its good generalization on long sequences, large-scale environments, and multi-step prediction, with analyses confirming that its advantages stem from explicit understanding of spatial structures. Building on this, we introduce Hippoformer, which integrates mm-TEM with Transformer to combine structural spatial memory with precise working memory, achieving superior generalization in both 2D and 3D prediction tasks and highlighting the potential of hippocampal-inspired architectures for complex domains. Overall, Hippoformer represents a initial step toward seamlessly embedding structured spatial memory into foundation architectures, offering a potential scalable path to endow deep learning models with spatial intelligence.
General Machine Learning · Transfer, Multitask and Meta-learning
Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) continual learning techniques often retain and freeze previously learned LoRAs or generate data representations to overcome forgetting, typically utilizing these to support new LoRAs learn new tasks. However, these methods not only ignore growing computational memory with tasks and limited storage space but also suffer from potential task interference due to the lack of effective LoRA merging mechanisms. In this paper, we propose a novel continual learning method that orthogonally initializes and sequentially merges LoRAs updates into a single unified LoRA. Our method leverages orthogonal basis extraction from previously learned LoRA to initialize the learning of new tasks, further exploits the intrinsic asymmetry property of LoRA components by using a time-aware scaling mechanism to balance new and old knowledge during continual merging. Our approach maintains constant memory complexity with respect to the number of tasks, minimizes interference between past and new tasks via orthogonal basis initialization, and improves performance over asymmetric LoRA merging via adaptive scaling. We provide theoretical analysis to justify our design and conduct extensive experiments across diverse continual learning benchmarks using various LLMs, demonstrating the effectiveness and efficiency of our method.
Deep Learning · Algorithms
The Euclidean distance between wavelet scattering transform coefficients (known as paths) provides informative gradients for perceptual quality assessment of deep inverse problems in computer vision, speech, and audio processing. However, these transforms are computationally expensive when employed as differentiable loss functions for stochastic gradient descent due to their numerous paths, which significantly limits their use in neural network training. Against this problem, we propose "Scattering transform with Random Paths for machine Learning" (SCRAPL): a stochastic optimization scheme for efficient evaluation of multivariable scattering transforms. We implement SCRAPL for the joint time–frequency scattering transform (JTFS) which demodulates spectrotemporal patterns at multiple scales and rates, allowing a fine characterization of intermittent auditory textures. We apply SCRAPL to differentiable digital signal processing (DDSP), specifically, unsupervised sound matching of a granular synthesizer and the Roland TR-808 drum machine. We also propose an initialization heuristic based on importance sampling, which adapts SCRAPL to the perceptual content of the dataset, improving neural network convergence and evaluation performance. We make our code and audio samples available and provide SCRAPL as a Python package.
We introduce PAT3D, the first physics-augmented text-to-3D scene generation framework that integrates vision–language models with physics-based simulation to produce physically plausible, simulation-ready, and intersection-free 3D scenes. Given a text prompt, PAT3D generates 3D objects, infers their spatial relations, and organizes them into a hierarchical scene tree, which is then converted into initial simulation conditions. A rigid-body simulator ensures realistic object interactions under gravity, driving the scene toward static equilibrium without interpenetrations. To further enhance scene quality, we introduce a simulation-in-the-loop optimization procedure that guarantees physical stability and non-intersection, while improving semantic consistency with the input prompt. Experiments demonstrate that PAT3D substantially outperforms prior approaches in physical plausibility, semantic accuracy, and visual quality. Beyond high-quality generation, PAT3D uniquely enables simulation-ready 3D scenes for downstream tasks such as scene editing and robotic manipulation. Our code and data are available at https://github.com/Simulation-Intelligence/PAT3D.
General Machine Learning · Representation Learning
Learning the intrinsic dimensionality of subjective perceptual spaces such as taste, smell, or aesthetics from ordinal data is a challenging problem. We introduce LORE (Low Rank Ordinal Embedding), a scalable framework that jointly learns both the intrinsic dimensionality and an ordinal embedding from noisy triplet comparisons of the form, "Is A more similar to B than C?". Unlike existing methods that require the embedding dimension to be set apriori, LORE regularizes the solution using the nonconvex Schatten-$p$ quasi norm, enabling automatic joint recovery of both the ordinal embedding and its dimensionality. We optimize this joint objective via an iteratively reweighted algorithm and establish convergence guarantees. Extensive experiments on synthetic datasets, simulated perceptual spaces, and real world crowdsourced ordinal judgements show that LORE learns compact, interpretable and highly accurate low dimensional embeddings that recover the latent geometry of subjective percepts. By simultaneously inferring both the intrinsic dimensionality and ordinal embeddings, LORE enables more interpretable and data efficient perceptual modeling in psychophysics and opens new directions for scalable discovery of low dimensional structure from ordinal data in machine learning.
Deep Learning · Algorithms
Deploying large language models (LLMs) on mobile platforms faces significant challenges due to the limited memory and shared computational resources of the device. Resource availability may be an issue as it is directly impacted by on the current device workload, adding to the uncertainty of model deployment. We introduce UniQL, a unified post-training quantization and low-rank compression framework, with on-device configurable pruning rates for edge LLMs. UniQL is a general framework that integrates quantization and low-rank compression for Transformers, State Space Models (SSMs), and hybrid models to cater to diverse edge applications. In our proposed joint framework, we introduce an efficient structured weight-sorting that speeds up the computation by 20×, quantization-aware singular value decomposition (SVD) decompositions to minimize the quantization errors, state-aware weight sorting for SSMs, and a fused rotary embedding (RoPE) kernel for the pruned models. Our framework performs weight-sorting, fine-tuning, and quantization in the cloud in a one-shot fashion, while enabling on-device configurable pruning rates up to 35%. Our experiments show that quantized and pruned models offer a memory reduction of 4×–5.7× and a token throughput improvement of 2.7×–3.4×, maintaining accuracy within 5% of the original models at 15% pruning rates across Transformers (Llama3 and Qwen2.5), SSMs (Mamba2), and hybrid models (Nemotron-H and Bamba-v2). The code and quantized models will be released at: https://github.com/enyac-group/UniQL.
Deep Learning · Generative Models and Autoencoders
Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV) caching, and incoherent generation arising from learning dependencies over an intractable space of token combinations. To address these limitations, we introduce ReFusion, a novel masked diffusion model that integrates sequence reorganization into the causal attention framework. By elevating parallel decoding from the token level to a higher slot level, ReFusion interleaves inter-slot diffusion-based selection with intra-slot autoregressive infilling, while reordering newly generated slots ahead of the remaining masks after each iteration. Consequently, this design simultaneously unlocks full KV cache reuse and reduces learning complexity from an intractable token combination space to a manageable slot-level permutation space. Extensive experiments on seven diverse benchmarks show that ReFusion not only overwhelmingly surpasses prior MDMs with a 34\% performance gain and an over 18$\times$ speedup on average, but also bridges the performance gap to strong ARMs while maintaining a 2.33$\times$ average speedup.
Deep Learning · Graph Neural Networks
Neural message passing serves as a cornerstone framework in graph neural networks, providing a clear and intuitive mathematical guideline for the propagation and aggregation of information among interconnected nodes within graphs. Throughout this process, node representations undergo dynamic updates, considering both the individual states and connections of neighboring nodes. Concurrently, social networks, as prominent forms of interconnected data, form dynamic systems that achieve stability through continuous internal communications and opinion exchanges among social actors along their social ties. Drawing upon the shared concepts between these two domains, our study establishes an explicit connection between message passing and opinion dynamics in sociology. Moreover, we introduce a novel continuous message passing scheme termed ODNet, which integrates bounded confidence to refine the influence weight of local nodes for message propagation. By adjusting the similarity cutoffs of bounded confidence and influence weights within ODNet, we define opinion exchange rules that align with the characteristics of neural message passing and can effectively mitigate the oversmoothing issue. We extend the framework to hypergraphs and formulate corresponding continuous message passing rules, which reveal a close association with particle dynamics. Empirically, we showcase that ODNet enhances prediction performance across various social networks presented as homophilic graphs, heterophilic graphs, and hypergraphs. Notably, our proposed ODNet outperforms existing GNNs with its straightforward construction and robust theoretical foundation.
Computer Vision · Vision Models & Multimodal
Information Bottleneck (IB) Theory is renowned for its ability to learn simple, compact, and effective data representations. In multi-modal clustering, IB theory effectively eliminates interfering redundancy and noise from multi-modal data, while maximally preserving the discriminative information. Existing IB-based multi-modal clustering methods suffer from low-quality pseudo-labels and over-reliance on accurate Mutual Information (MI) estimation, which is known to be challenging. Moreover, unreliable or noisy pseudo-labels may lead to an overconfident clustering outcome. To address these challenges, this paper proposes a novel CaLibrated Information Bottleneck (CLIB) framework designed to learn a clustering that is both accurate and trustworthy. We build a parallel multi-head network architecture—incorporating one primary cluster head and several modality-specific calibration heads—which achieves three key goals: namely, calibrating for the distortions introduced by biased MI estimation thus improving the stability of IB, constructing reliable target variables for IB from multiple modalities and producing a trustworthy clustering result. Notably, we design a dynamic pseudo-label selection strategy based on information redundancy theory to extract high-quality pseudo-labels, thereby enhancing training stability. Experimental results demonstrate that our model not only achieves competitive clustering accuracy on multiple benchmark datasets but also exhibits excellent performance on the expected calibration error metric. Code is available at \textcolor{red}{https://shizhehu.github.io/}.