论文检索

Deep Learning · Generative Models and Autoencoders

Chenyang Xu, Dezhen Wang, Lin Chen, Kepeng Lin, Hao Wang

Accelerating diffusion models via feature caching has evolved from static reuse to polynomial extrapolation, yet current "cache-then-forecast" strategies remain limited by rigid, hand-crafted approximation families (e.g., Taylor or Hermite bases) that often misalign with the complex, layer-specific non-stationarity of generative feature dynamics. This paper introduces EigenCache, a theoretically grounded framework that re-frames acceleration as a problem of covariance learning and experimental design. By modeling feature trajectories as time-indexed stochastic processes governed by learnable temporal kernels, we demonstrate that the statistically optimal feature predictor (Minimum Mean Squared Error) is the Gaussian Process posterior mean (Kriging), which strictly generalizes and outperforms previous fixed-basis expansions. Crucially, this probabilistic formulation couples prediction with uncertainty quantification via a closed-form variance certificate. Leveraging this, we derive an information-theoretic scheduling algorithm that selects computation anchors by maximizing the log-determinant of the posterior covariance—a submodular objective that admits a provably near-optimal greedy solution. EigenCache thus provides a unified, training-free foundation for efficient inference, offering not only superior reconstruction accuracy but also a rigorous mechanism for robust, uncertainty-aware compute allocation.

Social Aspects · Fairness

Jairo Diaz-Rodriguez

Machine learning research increasingly bifurcates into two disconnected modes: benchmark-driven engineering that prioritizes metrics over understanding, and idealized theory that often fails to transfer to modern systems . In this position paper, we argue that the field focuses too heavily on these endpoints, neglecting the central scientific object: the idea. We propose an Ideas First framework in which *ideas* are valued for the behavioral *signatures* they predict in modern models, and these signatures are tested through *tailored experiments* designed to detect the relevant patterns rather than to win leaderboards. This shift not only bridges the gap between theory and practice but also promotes equity by removing the "complexity premium", enabling rigorous scientific contributions from researchers with modest computational, financial, and human resources. Ultimately, we advocate for a research culture centered on ideas, treating benchmarks and theorems as instruments for testing mechanistic hypotheses rather than as ends in themselves.

Optimization · Large Scale, Parallel and Distributed

Kaoru Otsuka, Yuki Takezawa, Makoto Yamada

Partial participation is essential for communication-efficient federated learning at scale, yet existing Byzantine-robust methods typically assume full client participation. In the partial participation setting, a majority of the sampled clients may be Byzantine, once Byzantine clients dominate, existing methods break down immediately. We introduce delayed momentum aggregation, a principle where the central server aggregates cached momentum from non-sampled clients along with fresh momentum from sampled clients. This principle ensures Byzantine clients remain a minority from the server's perspective even when they dominate the sampled set. We instantiate this principle in our optimizer DeMoA. We analyze the convergence rate of DeMoA, showing that DeMoA is Byzantine-robust under partial participation. Experiments show that, with 20% Byzantine ratio and only 10% partial participation rate, DeMoA achieves the best accuracy even when existing methods fail empirically.

Deep Learning · Generative Models and Autoencoders

Cong Geng, Xue Han, Ye Yuan, Qiang Hu, Xin Huang, Ruiqiao Bai, JUNLAN FENG

Energy-based models (EBMs) provide a flexible framework for generative models with strong distribution modeling capabilities. Nevertheless, their broader adoption has been limited by the difficulty of stable and efficient training. In this paper, we propose a unified and efficient latent-guided cooperative EBM that leverages informative target latent variables to guide the joint energy in capturing both data distribution and semantic structure, along with a cooperative generator designed for effective MCMC initialization. Our joint space optimization only requires MCMC sampling in the data space, and allows the energy to learn semantic data–latent relationships directly from real data. Experiments show our method improves generation quality and training stability with fewer resources, and performs effectively across multiple downstream tasks.

General Machine Learning · Transfer, Multitask and Meta-learning

Junpeng Ren, Carlos Misael Madrid Padilla, Yanzhen Chen, OSCAR HERNAN MADRID PADILLA

This paper develops a general transfer learning framework for nonparametric regression with heterogeneous data consisting of multiple groups. Under the assumption that groups share a common structure along with group-specific deviations in additive form, the proposed method employs a two-stage offset learning procedure: the first stage pools data from all groups to estimate an overall mean function, and the second stage estimates offsets for each group, yielding final group-level estimators through additive combination. Non-asymptotic upper bounds are established for the proposed framework, covering a broad class of nonparametric estimators under mild complexity and noise conditions. When instantiated with deep ReLU networks, explicit convergence rates are derived under hierarchical composition models, demonstrating the ability to overcome the curse of dimensionality. Conditions that enable positive transfer with faster rates are considered, including learning with simpler functions and data augmentation through pooling samples across groups. Various simulations and real-data experiments further validate the effectiveness of the proposed method.

Reinforcement Learning · Planning

Zergham Ahmed, Josh Tenenbaum, Chris Bates, Samuel Gershman

Modern reinforcement learning (RL) systems have demonstrated remarkable capabilities in complex environments, such as video games. However, they still fall short of achieving human-like sample efficiency and adaptability when learning new domains. Theory-based reinforcement learning (TBRL) is an algorithmic framework specifically designed to address this gap. Modeled on cognitive theories, TBRL leverages structured, causal world models---``theories''---as forward simulators for use in planning, generalization and exploration. Although current TBRL systems provide compelling explanations of how humans learn to play video games, they face several technical limitations: their theory languages are restrictive, and their planning algorithms are not scalable. To address these challenges, we introduce TheoryCoder, an instantiation of TBRL that exploits hierarchical representations of theories and efficient program synthesis methods for more powerful learning and planning. TheoryCoder equips agents with general-purpose abstractions (e.g., ``move to''), which are then grounded in a particular environment by learning a low-level transition model (a Python program synthesized from observations by a large language model). A bilevel planning algorithm can exploit this hierarchical structure to solve large domains. We demonstrate that this approach can be successfully applied to diverse and challenging grid-world games, where approaches based on directly synthesizing a policy perform poorly. Ablation studies demonstrate the benefits of using hierarchical abstractions.

Deep Learning · Large Language Models

Kyungjin Im, Chanin Eom, Miru Kim, Minhae Kwon

Model merging has become a practical post-training strategy for building a single multi-task large language model (LLM) by combining multiple task-specialized models, avoiding costly joint training. However, most existing approaches rely on post-hoc merging, in which task-specific models are merged only once after training. This one-shot aggregation often suffers from task interference, leading to *information erasure* across individual tasks. In this work, we show that replacing post-hoc merging with an iterative *many-shot merging* protocol is effective in improving multi-task performance. Building on this insight, we propose **METIS**, **M**itigating **E**rasure from **T**ask **I**nterference for **S**table many-shot merging. METIS is a loss-aware many-shot merging method that stabilizes iterative integration through task-wise loss-gap weighting and consensus-based masking. Notably, METIS exhibits significant performance improvement on the worst-performing task, effectively mitigating information erasure.

Deep Learning · Large Language Models

Seyed Morteza Emadi

Attention scores in transformers are bilinear forms $S_{ij} = x_i^\top M x_j / \sqrt{d_h}$ whose maximum magnitude governs overflow risk in low-precision training. We derive a \emph{rank-aware concentration inequality}: when the interaction matrix $M = W^Q W^{K\top}$ has rank $r \ll d$, tail probabilities for $\max_{i,j}|S_{ij}|$ decay as $\exp(-d^2\alpha^2/r)$ rather than $\exp(-d\alpha^2)$, an improvement of $d/r$ in the exponent. For transformer attention where $r = d_h$, this yields $25$--$64\times$ tighter concentration than rank-agnostic bounds in modern architectures. We apply this result to FP8 training, deriving *geometry-aware scale factors* that provide provable overflow guarantees without observing activations. The method computes per-layer scales from the spectral norm $\|W^Q W^{K\top}\|_2$ via implicit power iteration, includes a grouped query attention formulation that avoids key expansion, and remains compatible with fused attention kernels. Across GPT-2 XL to Llama-2-70B, geometry-aware scaling eliminates overflows in transient scenarios where delayed scaling fails, while matching downstream MMLU accuracy.

Applications · Robotics

Lukas Lao Beyer, Sertac Karaman

Deep learning methods have vastly expanded the capabilities of motion planning in robotics applications, as learning priors from large-scale data has been shown to be essential in capturing the highly complex behavior required for solving tasks such as manipulation or navigation for autonomous vehicles. At the same time, model-based planning algorithms based on search or optimization remain an essential tool due to their flexibility, efficiency, and the ability to incorporate domain knowledge via expert-designed algorithms and objective functions. We propose a new generative framework to unify these two paradigms. First, we learn an autoencoder with a high compression ratio and a latent space of hierarchically ordered, discrete-valued tokens. Leveraging both the dimensionality reduction and the hierarchical coarse-to-fine structure learned by this autoencoder, we then perform motion planning by directly searching in the latent space of tokens. This search can optimize arbitrary objective functions specified at test time, providing a large degree of flexibility while maintaining efficiency and producing realistic solutions by relying on the generative capabilities of the highly compressed autoencoder. We evaluate our method on nuPlan and the Waymo Open Motion Dataset, showing how latent space search can be used for a variety of guided behavior generation tasks, achieving strong performance for closed-loop motion planning and multi-agent guided scenario synthesis without requiring any task-specific training.

General Machine Learning · Transfer, Multitask and Meta-learning

Yavuz Yarici, Ghassan AlRegib

Deploying multimodal models in real-world scenarios requires generalization to new environments where recording conditions differ from training, a challenge known as multimodal domain generalization (MMDG). Standard architectures employ separate encoders for each modality and a fusion module, training the system end-to-end by optimizing on the fused features. In this paper, we identify that such joint optimization causes encoders to exploit cross-modal co-occurrences, statistical relationships between modalities that arise from source-specific recording conditions, rather than learning domain-invariant features. We term this failure mode Fusion Overfitting. To address this, we propose Modality-Entropy Regularization for Domain Generalization (MER-DG), which maximizes the entropy of each encoder's feature distribution to preserve feature diversity. MER-DG is architecture-agnostic and integrates into existing multimodal frameworks as an additive loss term. Extensive experiments on EPIC-Kitchens and HAC benchmarks demonstrate average improvements of ${\sim}5\%$ over standard fusion and ${\sim}2\%$ over state-of-the-art methods.

Deep Learning · Large Language Models

Xingyu Ma, Xin Tian, Lingxiang Wu, Xuepeng Wang, Zhilin Zhang, Xueming Tang, Jinqiao Wang

In recent years, significant advancements in large language models have greatly propelled the development of Text-to-SQL tasks. However, due to the token-by-token sequential generation mechanism employed by these models, they encounter a semantic blind spot problem with respect to pending SQL components—the parts of the SQL query yet to be generated. Specifically, language models are unable to effectively utilize the semantic information of these pending SQL components during the generation of the final SQL query, which poses considerable challenges for generating complex SQL statements. To address this issue, we propose a novel thought process based on SQL components pre-generation and design a maximum connected subtree matching reward mechanism leveraging the SQL abstract syntax tree to improve the accuracy of local component generation. Extensive experiments demonstrate that, under comparable model parameter scales, our training approach achieves significant advantages, effectively enhancing the generation of complex SQL queries. Our method attains an execution accuracy EX of 65.78% on the BIRD-dev dataset and achieves state-of-the-art performance on the Spider-syn datasets.

Deep Learning · Sequential Models, Time series

Homanga Bharadhwaj

The AI community is rapidly converging on generalist foundation models trained on web-scale data. While this paradigm has yielded impressive gains, in this paper we argue that this objective needs to shift for enabling AI that reliably helps people in their daily activities. The most valuable systems will not be those that attempt do everything for everyone, but those that do the right things for a specific individual over a long period of time. We take the position that \emph{specialist models}---defined not by narrow task taxonomies, but by a tight coupling to an individual user and their local environment---represent the endgame for high-impact assistive AI. We substantiate this argument through three case studies: (i) AI agents that need to help humans automate daily web activities; (ii) wearable assistants that must predict actions in-context from continuous egocentric streams; and (iii) home robots that require helping humans in daily tasks with safety and compliance guarantees. In these settings, standard scaling assumptions are inverted: the most critical data is generated \emph{after deployment} as a streaming, on-policy interaction trace. We outline research directions for building specialists that learn from organic observational data, avoid self-reinforcing errors, and improve safely over long horizons.

General Machine Learning · Causality

Zheng Li, Feng Xie, Shenglan Nie, Xichen Guo, Ruxin Wang, Hao Zhang

Constraint-based causal discovery is widely used for learning causal structures, but heavy reliance on conditional independence (CI) testing makes it computationally expensive in high-dimensional settings. To mitigate this limitation, many divide-and-conquer frameworks have been proposed, but most assume causal sufficiency, i.e., no latent variables. In this paper, we show that divide-and-conquer strategies can be theoretically generalized beyond causal sufficiency to settings with latent variables. Specifically, we propose a recursive decomposition framework, termed DiCoLa, that enables divide-and-conquer causal discovery in the presence of latent variables. It recursively decomposes the global learning task into smaller subproblems and integrates their solutions through a principled reconstruction step to recover the global structure. We theoretically establish the soundness and completeness of the proposed framework. Extensive experiments on synthetic data demonstrate that our approach significantly improves computational efficiency across a range of causal discovery algorithms, while experiments on a real-world dataset further illustrate its practical effectiveness.

Deep Learning · Large Language Models

Yanhua Jiao, Tianyi Wu, Xiaoxi Sun, Yulin Li, Huiling Zhen, Libo Qin, Baotian Hu, Zhuotao Tian, Min zhang

While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conservative confidence thresholds. These thresholds, necessitated by the Joint Probability Dependence Error (JPDE), result in redundant denoising iterations and suboptimal inference speeds. To overcome this, we propose DC-Leap, a training-free framework that enables reliable acceleration of dLLMs in the moderate-confidence regime. DC-Leap introduces a Dynamic Contiguous Verification strategy that integrates strictly-ordered causal constraints into the parallel decoding process. By progressively validating token dependencies, this mechanism effectively neutralizes the JPDE, enabling reliable acceleration with near-lossless performance. Furthermore, DC-Leap incorporates the draft-guided decoding mechanism, where the draft helps extend the context by leaping forward across multiple tokens, providing look-ahead context and retaining the structural benefits of bidirectional attention during inference. Extensive experiments on standard benchmarks demonstrate that DC-Leap achieves substantial speedups, up to **53.19$\times$** on MBPP for long-sequence generation, and up to **105.02$\times$** when combined with KV-Cache with comparable generation quality. Code and models will be made publicly available.

Applications · Language, Speech and Dialog

Deepak Piskala

This position paper argues that the machine learning community should prioritize speech-native architectures that treat audio as a first-class modality, anticipating the inevitable shift from text-dominated to speech-first data distributions. Text dominates human-computer interaction not because it is cognitively natural, but because decades of interface design conditioned users to express knowledge through keyboards and search boxes. Recent advances in speech recognition and multimodal foundation models have removed the technical barriers to voice-based interaction; what remains is primarily a habit problem. As voice becomes habitual, the data ecosystem underlying machine learning will shift toward speech-native knowledge—with profound implications for model architecture, training efficiency, and evaluation paradigms. This paper examines the technical readiness of speech systems, identifies habit inertia as the primary adoption barrier, addresses alternative views that favor text-centric approaches, and outlines a research agenda for ML systems that anticipate speech-first data distributions.

Deep Learning · Attention Mechanisms

Xinghao Wang, Pengyu Wang, Dong Zhang, Chenkun Tan, Shaojun Zhou, Zhaoxiang Liu, Shiguo Lian, Fangxu Liu, Kai Song, Xipeng Qiu

Scaling the context length of large language models (LLMs) offers significant benefits but is computationally expensive. This expense stems primarily from the self-attention mechanism, whose $O(N^2)$ complexity with respect to sequence length presents a major bottleneck for both memory and latency. Fortunately, the attention matrix is often sparse, particularly for long sequences, suggesting an opportunity for optimization. Block-sparse attention has emerged as a promising solution that partitions sequences into blocks and skips computation for a subset of these blocks. However, the effectiveness of this method is highly dependent on the underlying attention patterns, which can lead to sub-optimal block-level sparsity. For instance, important key tokens for queries within a single block may be scattered across numerous other blocks, leading to computational redundancy. In this work, we propose Permuted Block-Sparse Attention (**PBS-Attn**), a plug-and-play method that leverages the permutation properties of attention to increase block-level sparsity and enhance the computational efficiency of LLM prefilling. We conduct comprehensive experiments on challenging long-context datasets, demonstrating that PBS-Attn consistently outperforms existing block-sparse attention methods in model accuracy and closely matches the full attention baseline. Powered by our custom permuted-FlashAttention kernels, PBS-Attn achieves an end-to-end speedup of up to $\mathbf{2.75\times}$ in long-context prefilling, confirming its practical viability. Code available at \url{https://anonymous.4open.science/r/pbs-attn-BB66}.

Applications · Robotics

Shijie Lian, Bin Yu, Xiaopeng LIN, Laurence Yang, Zhaolong Shen, Changti Wu, YuZhuo Miao, Cong Huang, Kai Chen

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where goal-driven data collection creates a dataset bias. In such datasets, language instructions are highly predictable from visual observations alone, causing the conditional mutual information between instructions and actions to vanish, a phenomenon we term Information Collapse. Consequently, models degenerate into vision-only policies that ignore language constraints. To address this, we propose LangForce, enforces instruction following via Bayesian decomposition. By introducing learnable Latent Action Queries, we construct a dual-branch architecture to estimate both a vision-only prior $p(a \mid v)$ and a language-conditioned posterior $\pi(a \mid v, \ell)$. We then optimize the policy to maximize the conditional Pointwise Mutual Information (PMI) between actions and instructions. This objective effectively penalizes the vision shortcut and rewards actions that explicitly explain the language command. Extensive experiments across on three benchmarks demonstrate substantial gains, including an 11.3\% improvement on the challenging OOD SimplerEnv benchmark, validating the ability of LangForce to robustly ground language in action.

Probabilistic Methods · Monte Carlo and Sampling Methods

Weihang Xu, Huajie Qian, Wotao Yin, Xinshang Wang

We study simultaneous confidence bounds for aggregated effects over downward-closed subset families of independent statistical tests. The bounds are obtained by bootstrap calibration of the maximum normalized aggregated effect over the relevant subset family, yielding valid post-hoc inference for data-selected subsets and tighter bounds than classical methods that protect all linear contrasts. A central challenge is that the required maximization is a nonlinear combinatorial optimization problem whose exact solution is essential for correct coverage. We address this challenge by casting the problem as a densest subgraph optimization and reformulating it as a linear program, or as a mixed-integer linear program when downward-closed linear constraints are imposed, enabling efficient and exact evaluation. We further characterize the growth regime of the number of tests for which the bootstrap calibration remains valid and illustrate the method on several machine learning applications.

Shufan Li, Yuchen Zhu, Jiuxiang Gu, Kangning Liu, Zhe Lin, Yongxin Chen, Molei Tao, Aditya Grover, Jason Kuen

Diffusion language models (dLLMs) recently emerged as a promising alternative to auto-regressive LLMs. The latest works further extended it to multimodal understanding and generation tasks. In this work, we propose LaViDa-R1, a multimodal, general-purpose reasoning dLLM. Unlike existing works that build reasoning dLLMs through task-specific reinforcement learning, LaViDa-R1 incorporates diverse multimodal understanding and generation tasks in a unified manner. In particular, LaViDa-R1 is built with a novel unified post-training framework that seamlessly integrates supervised finetuning (SFT) and multi-task reinforcement learning (RL). It employs several novel training techniques, including answer-forcing, tree search, and complementary likelihood estimation, to enhance effectiveness and scalability. Extensive experiments demonstrate LaViDa-R1's strong performance on a wide range of multimodal tasks, including visual math reasoning, reason-intensive grounding, and image editing.

Chuyi Tan, Peiwen Yuan, Xinglin Wang, Yiwei Li, Shaoxiong Feng, Yueqi Zhang, Jiayi Shi, Ji Zhang, Boyuan Pan, Yao Hu 等

Reinforcement learning with verifiable rewards (RLVR) efficiently scales the reasoning ability of large language models but is bottlenecked by scarce labeled data. Reinforcement learning with intrinsic rewards (RLIR) offers a scalable alternative via self-rewarding, yet often suffers from instability and inferior performance. We trace this gap to a systemic bias in confidence-coupled self-rewarding: the model tends to over-reward high-confidence mistakes, forming a \textbf{self-confirming loop}. We quantify this feedback-loop bias with three metrics: reward noise magnitude ($\rho_{\text{noise}}$), policy–reward coupling ($\rho_{\text{selfbias}}$), and over-/under-reward skew ($\rho_{\text{symbias}}$). Our analyses show a compounding effect where strong coupling amplifies confidence-conditioned errors and drives a drift toward over-reward, leading to instability and a lower performance ceiling. To mitigate this, we propose reinforcement learning with ensembled rewards (\textbf{RLER}), which aggregates diverse models with adaptive reward interpolation and disagreement-aware rollout selection to reduce coupling and suppress over-reward drift. Extensive experiments show that RLER improves by 13.6\% over the best RLIR baseline and is within 3.6\% of RLVR, while exhibiting stable scaling on unlabeled samples.