论文检索

Applications · Robotics

Yixian Chen, Rufan Bai, Jiangbin Zheng, Yimin Wang, Tiantian CHEN, Wei Wang, Yuhuan Lu

Autonomous vehicles operating in open-world environments must continually adapt to rare long-tail scenarios while preserving previously acquired driving skills. However, existing trajectory planning approaches struggle with this stability-plasticity trade-off, as they rely on static models or rigid rule-based controllers that cannot robustly handle evolving and complex traffic dynamics. Against this background, we propose **NOMAD**, a lifelong trajectory planning framework that integrates non-parametric Bayesian memory with diffusion-based trajectory generation, enabling continuous adaptation to long-tail scenarios without catastrophic forgetting. Our method maps continuous scene contexts to a dynamically growing set of discrete memory clusters, which guide a conditional diffusion model to function as a mixture of experts specialized for diverse driving behaviors. To retain past knowledge during incremental learning, we introduce a generative replay mechanism that synthesizes pseudo-experiences from previously learned memory clusters. Extensive closed-loop evaluations on the nuPlan benchmark demonstrate that our approach achieves state-of-the-art performance on long-tail scenarios, improving the interPlan score by **9.4\%** over the strongest baseline, while maintaining competitive performance on regular driving benchmarks. Moreover, our method exhibits robust continual learning capability, achieving the highest average closed-loop score with positive backward transfer when adapting to sequentially introduced long-tail scenarios.

Deep Learning · Robustness

William Zhang, Saurabh Amin, Georgia Perakis

Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling process as a black box, overlooking opportunities to exploit and understand modular structure. We introduce a conformal prediction framework for two-stage sequential models, where an upstream predictor generates intermediate representations for a downstream model. By decomposing the overall prediction residual into stage-specific components, our method enables practitioners to attribute uncertainty to specific pipeline stages. We develop a risk-controlled parameter selection procedure using family-wise error rate (FWER) control to calibrate stage-wise scaling parameters, and introduce an adaptive extension for non-stationary settings. Experiments on synthetic distribution shifts, as well as real-world supply chain and stock market data, demonstrate that our approach improves coverage under structural, stage-wise shifts compared to standard conformal methods, while identifying stage-wise error contribution. This framework offers diagnostic advantages and robust coverage that standard conformal methods lack.

Reinforcement Learning · Batch/Offline

Mingxuan Li, Junzhe Zhang, Elias Bareinboim

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy gradients, which assume that there is no unmeasured confounding in the data. However, this condition does not necessarily hold for pixel-based demonstrations when a mismatch exists between the demonstrator's and the learner's sensory capabilities, leading to implicit confounding biases in offline data. We address the challenge by investigating the problem of confounded observations in offline RL from a causal perspective. We develop a novel causal offline RL objective that optimizes policies' worst-case performance that may arise due to confounding biases. Based on this new objective, we introduce a practical implementation that learns expressive flow-matching policies from confounded demonstrations, employing a deep discriminator to assess the discrepancy between the target policy and the nominal behavioral policy. Experiments across 25 pixel-based tasks demonstrate that our proposed confounding-robust augmentation procedure achieves a success rate 120\% that of confounding-unaware, state-of-the-art offline RL methods.

Deep Learning · Algorithms

Jingze Shi, Zhangyang Peng, Yizhang Zhu, Yifan WU, Guang Liu, Yuyu Luo

Mixture-of-Experts (MoE) architectures are evolving towards finer granularity to improve parameter efficiency. However, existing MoE designs face an inherent trade-off between the granularity of expert specialization and hardware execution efficiency. In this paper, we propose OmniMoE, a system-algorithm co-designed MoE framework that pushes granularity to the extreme with vector-level Atomic Experts, orchestrating their routing and execution at scale within a single MoE layer, while retaining a shared dense MLP for general-purpose processing. While this atomic design maximizes capacity, it poses severe challenges for routing complexity and memory access. To address these, OmniMoE adopts a system-algorithm co-design: (i) a Cartesian Product Router that decomposes the massive index space to reduce routing complexity from $O(N)$ to $O(\sqrt{N})$; and (ii) Expert-Centric Scheduling that inverts the execution order to turn scattered, memory-bound lookups into efficient dense matrix operations. Validated on seven benchmarks, OmniMoE (with 1.7B active parameters) achieves 50.9\% zero-shot accuracy across seven benchmarks, outperforming coarse-grained (e.g., DeepSeekMoE) and fine-grained (e.g., PEER) baselines. Crucially, OmniMoE reduces inference latency from 73ms to 6.7ms (a 10.9$\times$ speedup) compared to PEER, demonstrating that massive-scale fine-grained MoE can be fast and accurate.

Applications · Neuroscience, Cognitive Science

JinGyo Lim, Seunggyu Jeong, Seong-Eun Kim

Recent Spiking Transformer models have explored a variety of attention mechanisms beyond standard dot-product formulations. However, many existing similarity-based spiking attention formulations remain inherently sensitive to firing density, causing neurons with high spike rates to dominate attention scores regardless of semantic relevance. This density bias is particularly problematic in event-driven spiking representations, where sparse spike patterns often carry critical information. To address this limitation, we rethink spiking attention from a set-theoretic perspective. We propose DiceFormer, a novel Spiking Transformer architecture driven by Spike Dice Attention (SDA). Unlike traditional approaches, SDA replaces density-sensitive measures with a set similarity function derived from the Dice coefficient. By explicitly normalizing for firing density, SDA focuses on spike co-occurrence rather than high firing rates. We primarily evaluate DiceFormer on the challenging audio domain, where spike sparsity varies substantially across inputs. On AudioSet-20k, DiceFormer achieves a SOTA mAP of 0.161 with 54.3M parameters, outperforming prior SNN-based approaches and substantially narrowing the performance gap with ANN-based models. We also introduce Lin-SDA, a linearized version for computation efficiency, while achieving performance comparable to SDA. Beyond audio, we evaluate the effectiveness of SDA on CIFAR-100 to verify its applicability to the vision domain.

Deep Learning · Large Language Models

Sean Choi, Myungheon Chin, Ernest Ryu

Tokenization is the first point of contact between large language models (LLMs) and text data, yet it has not been viewed by many as a component of LLMs worth accelerating. During inference, tokenizers typically rely on simple dictionary lookups and are executed on CPUs as standard processes. This approach, however, introduces significant overhead from scheduling delays, core selection, data copying, and other system-level costs. These inefficiencies become problematic in latency-sensitive applications such as embedding, small language models, and agentic AI. In this paper, we present the Pinned Tokenizer (PinTok), a novel tokenizer architecture that reduces redundant hardware, operating system, and networking overhead through three key innovations: core and memory pinning, scheduling and context switch avoidance, and duplicate network packet copy and processing avoidance. Our implementation of PinTok can serve as a drop-in replacement for existing tokenizer deployments, delivering latency reductions of up to 95% (average), 97% (P50), 94% (P90), and 87% (P99) along with throughput improvements of up to 2,084%.

Applications · Language, Speech and Dialog

Yong Ren, Jingbei Li, Haiyang Sun, Yujie Chen, Cheng Yi, Yechang Huang, Hao Gu, Ye Bai, Xuerui Yang

Recent advances in Large Audio Language Models (LALMs) have extended Text-to-Speech (TTS) to interactive role-play scenarios, which demand high expressiveness and strict adherence to role-play instructions. However, existing models struggle to maintain stylistic consistency with character profiles and scene descriptions across multi-turn dialogues. A critical bottleneck is the lack of objective metrics for quantifying speaking style. To bridge this gap, we propose **Mean Continuation Log-Probability (MCLP)** as both an evaluation metric and a reward signal, validated on LALM-based Role-Play TTS (RP-TTS) tasks. Critically, we leverage the In-Context Learning capability of pre-trained LALMs to formulate MCLP via a continuation log-probability prediction. This metric quantifies stylistic consistency by measuring the likelihood of the ground-truth speech conditioned on the generated speech. Furthermore, we employ MCLP as a reinforcement learning reward to enhance the style alignment between generated speech and Role-Play instructions. To facilitate evaluation, we construct an RP-TTS dataset with rich scene and character annotations. Experimental results demonstrate that our method significantly outperforms strong LALM baselines on both objective and subjective metrics. Audio samples are available at https://mclp-tts.github.io/mclp/.

Applications · Time Series

YingHao Ai, Yukai Zhou, Ruoxi Jiang, Junyi An, Chao Qu, Zhijian Zhou, Shiyu Wang, Fenglei Cao, Zenglin Xu, Furao Shen 等

Spatio-temporal forecasting is critical for real-world applications like traffic management, yet capturing complex interactions under high-noise conditions remains challenging. While current methods have shown improved accuracy using spatial physical priors, they often struggle with evolving temporal correlations and systematic errors. In this work, we propose a nested forecasting framework that couples future macro-level regional trends with micro-level historical observations, enabling top-down guidance from abstract future representations for fine-grained forecasting. Specifically, we construct semantically coherent regions via spectral clustering and design a progressive coarse-to-fine predictor to inject macro-dynamics into node-level forecasting. Extensive experiments on multiple real-world datasets demonstrate that our method consistently outperforms state-of-the-art baselines, validating the effectiveness of future macro-guided nested forecasting.

Optimization · Convex

Junhyeong Lee, Sangjin Jin, Yongjae Lee

Decision-Focused Learning (DFL) trains predictors to improve downstream decision quality, but computing regret gradients typically requires differentiating through solvers or relying on surrogate losses, which can be computationally expensive or deviate from the true objective. We show that, under standard regularity with locally stable active constraints, the regret gradient admits a closed-form geometric characterization, equivalent to the prediction error projected onto the tangent space of active constraints, scaled by lo- cal curvature. This reveals that regret gradients can be obtained by filtering decision-irrelevant components from the MSE gradient, providing a simpler and more direct alternative to existing approaches. Based on this, we propose PEAR (Projected Error As Regret-gradient), which computes regret gradients via a reduced linear system over active constraints, avoiding differentiation through solver iterations or additional optimization solves. Experiments on LP benchmarks and a real-world QP task show that PEAR achieves the best decision quality among all baselines while being the most computationally efficient, with gains that persist under constraint shifts.

Deep Learning · Other Representation Learning

Jianqiao Zeng, Ruocheng Wang, Yanzhi Liu, Hao Xiong, Junchi Yan

Despite the fast progress in neural operator learning, long-sequence modeling still is a standing challenge whereby latent states have been introduced with techniques well derived. Diverging from existing methods that treat latent states as transient variables or decoupled representations, CoEvol-NO introduces a {persistent state} to establish a {co-evolutionary framework}, where the latent state and mesh sequence are updated jointly and bidirectionally. Inspired by classical numerical methods, we model the layer-wise state evolution as a {Predictor-Corrector (PC)} process. Specifically, a ``Predictor'' generates a tentative target, followed by a ``Corrector'' that refines the persistent state via an {error-driven update mechanism}. Furthermore, our theoretical analysis reveals that the widely used \textit{direct substitution} and \textit{residual update} paradigms are essentially {first-order approximations} of this error-driven correction under different loss assumptions. We theoretically prove that CoEvol-NO achieves strict {linear time complexity}. Extensive experiments on five standard benchmarks and two large-scale industrial design tasks demonstrate that CoEvol-NO consistently achieves {state-of-the-art (SOTA)} performance.

Applications · Health / Medicine

Jiahao Kuang, Nuowei Liu, Changzhi Sun, Jie Wang, Tao Ji, Yuanbin Wu

Function-guided protein design is a crucial task with significant applications in drug discovery and enzyme engineering. However, the field lacks a unified and comprehensive evaluation framework. Current models are assessed using inconsistent and limited subsets of metrics, which prevents fair comparison and a clear understanding of the relationships between different evaluation criteria. To address this gap, we introduce **PDFBench**, the first comprehensive benchmark for function-guided de novo protein design. Our benchmark systematically evaluates eight state-of-the-art models on 16 metrics across two key settings: description-guided design, for which we repurpose the Mol-Instructions dataset, originally lacking quantitative benchmarking, and keyword-guided design, for which we introduce a new test set, SwissTest, created with a strict datetime cutoff to ensure data integrity. By benchmarking across a wide array of metrics and analyzing their correlations, **PDFBench** enables more reliable model comparisons and provides key insights to guide future research.

Reinforcement Learning · Deep RL

Lirui Luo, Guoxi Zhang, Hongming Xu, Cong Fang, Qing Li

In DRL, an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from \emph{plasticity loss}: their ability to learn new skills from new experiences diminishes over training. Recently, Mixture-of-Experts (MoE) networks have been reported to enable scaling laws and facilitate the learning of diverse skills. However, in continual reinforcement learning settings, their performance can degenerate as learning proceeds, indicating a loss of plasticity. To address this, building on Neural Tangent Kernel (NTK) theory, we formalize the plasticity loss in MoE policies as a loss of \emph{spectral plasticity}. We then derive a tractable proxy for spectral plasticity, one expressible in terms of individual expert feature matrices. Leveraging this proxy, we introduce \emph{SPHERE}, a practical Parseval penalty tailored for MoE-based policies that alleviates the loss of spectral plasticity. On MetaWorld and HumanoidBench, SPHERE improves average success under continual RL by 133\% and 50\% over an unregularized MoE baseline, while maintaining higher spectral plasticity throughout training.

Social Aspects · Everything Else

Harry Jiang, Baris Askin, Gauri Joshi, Carlee Joe-Wong

Machine learning (ML) systems have grown significantly in size and popularity over recent years. However, the data and computation power supply chains which have helped fuel this growth have not been built without controversy. In particular, some of the data used to train these models may have been used without permission, while the growing appetite for compute power in model training increasingly incentivizes consolidation of access to larger players. As some stakeholders, such as data owners and everyday consumers of the Internet, have felt left behind by the emerging ML ecosystem, we seek to use federated learning paradigm as a model and motivation to develop a more democratized future for the ML community: one that is more decentralized, cooperative, and accountable. This position paper argues that the original proposition of federated learning as a framework enabling cooperation, privacy, and decentralization is still relevant today, even after the emergence of large foundation model- and scaling law-driven ML research, and that FL can inspire alternative ML ecosystems which alleviate and avoid the current frictions of large ML systems.

Deep Learning · Large Language Models

Dezhuang Miao, Xiaoming Zhang, Bo Zhang, Yibin Du, Xiang Li, Ruilin Zeng, Yirui QI

LLM-to-KG systems frequently fail on exclusion-rich questions because natural-language negation is both scope-sensitive and evidence-dependent: it may constrain only one subgoal/branch and only certain supporting paths, yet such attachment is rarely explicit in text. We propose the Executable Exchange Contract (EEC) to bridge this gap, specifying scope-bound exclusions as executable control metadata exchanged between a specifier and an executor. Our executor, MatLogic, compiles exclusions into scope-local masks applied during multi-hop propagation and executes requests under a unified P$\rightarrow$N$\rightarrow$C/D schedule, ensuring exclusions are enforced before witness loss and branch entanglement. The system can also return compact witness pointers to keep support types distinguishable when needed. We evaluate on both structured complex queries and end-to-end natural-language KGQA, and introduce contract-aligned diagnostics that isolate errors from specification versus execution and verify the necessity of scoped enforcement.

Deep Learning · Theory

William Merrill, Hongjian Jiang, Yanhong Li, Anthony Lin, Ashish Sabharwal

The community is increasingly exploring linear RNNs (LRNNs) as language models, motivated by their expressive power and parallelizability. While prior work establishes the expressivity benefits of LRNNs over transformers, it is unclear what makes LRNNs---but not traditional, *nonlinear* RNNs---as easy to parallelize in practice as transformers. We answer this question by providing a tight connection between types of RNNs and standard complexity classes. We show that LRNNs can be viewed as log-depth (bounded fan-in) arithmetic circuits, which represents only a slight depth overhead relative to log-depth boolean circuits that transformers admit. Furthermore, we show that nonlinear RNNs can solve $\mathsf L$-complete problems (and even $\mathsf P$-complete ones, under polynomial precision), revealing a fundamental barrier to parallelizing them as efficiently as transformers. Our theory also identifies fine-grained expressivity differences between recent popular LRNN variants: permutation-diagonal LRNNs are $\mathsf{NC}^1$-complete whereas diagonal-plus-low-rank LRNNs are more expressive ($\mathsf{PNC}^1$-complete). We provide further insight by associating each type of RNN with a corresponding automata-theoretic model that it can simulate. Together, our results reveal fundamental tradeoffs between nonlinear RNNs and different variants of LRNNs, providing a foundation for designing LLM architectures that achieve an optimal balance between expressivity and parallelism.

Applications · Computer Vision

Antoine Schnepf, Karim Kassab, Flavian Vasile, Andrew Comport

The generation of immersive and navigable 3D environments is increasingly prevalent with the growing adoption of virtual reality and 3D content. However, recent methods face a fundamental limitation: they cannot produce 3D worlds that simultaneously (i) are navigable over long-range spatial extents and (ii) cover the complete omnidirectional field of view ($360^\circ$ horizontally and $180^\circ$ vertically). To address this challenge, we introduce SphericalDreamer, a method for generating fully immersive and long-range 3D environments from textual prompts. Our approach is built on the generation of multiple panoramic images, which are subsequently lifted into 3D and fused together while maintaining visual and geometric consistency. SphericalDreamer produces highly detailed, fully immersive 3D environments, while substantially improving scale and navigability compared to prior approaches.

Deep Learning · Graph Neural Networks

Xuan Minh Vuong Nguyen, Nissrine Akkari, Fabien Casenave, Jonathan Viquerat, Elie Hachem

Graph Neural Networks (GNNs) on meshes have emerged as promising surrogates for computational mechanics, but standard local message passing struggles to propagate information across unstructured meshes, leading to large errors in regions with complex physics (e.g., shocks, wakes, boundary layers). Existing approaches enlarge connectivity with long-range edges chosen *a priori* via geometric heuristics or random sampling, which lack a mechanism to prioritize high-error regions and often introduce redundant communication. We propose **MiSe-GNN**, a dual-head architecture that adaptively augments graph connectivity using model-predicted *a posteriori* errors. MiSe-GNN jointly predicts physical fields and a node-wise error indicator; the predicted error is periodically converted into a hierarchy of additional edges via an adaptive tree that links high-error nodes to spatial pivots at multiple scales. This error-guided connectivity concentrates message passing where the surrogate is uncertain while keeping the graph sparse elsewhere, yielding a transparent and physically interpretable graph-space analogue of adaptive mesh refinement. Across industrial CFD and CSD benchmarks, MiSe-GNN consistently improves accuracy and accuracy–compute trade-offs over strong baselines, and qualitative analyses show that it routes communication toward physically challenging regions. These results establish *error-guided edge augmentation* as a robust and general design principle for long-range message passing in physics-aware GNNs.

Applications · Computer Vision

Hao Liu, Yi Zhou, Yanni Ma

Voxel-based 3D object detectors typically discretize the spatial domain using a uniform Cartesian grid, which allocates the same voxel size to both near-range and far-range regions. However, this uniform discretization is suboptimal for small objects such as pedestrians and cyclists, as they occupy only a few voxels and thus struggle to capture fine-grained geometric details. Although increasing the global voxel resolution can alleviate this problem, it inevitably increases substantial memory consumption and computational overhead. In this paper, we propose Radial Scaling Voxelization (RSV), a simple yet effective non-uniform discretization strategy that adaptively modulates the effective voxel size based on the radial distance from the LiDAR sensor. Unlike previous cylindrical or polar discretization schemes, RSV preserves the Cartesian grid topology by applying a continuous radial scaling function to the input coordinates before standard voxelization. This operation yields a near-high, far-unchanged resolution pattern: the effective voxel size becomes finer in near regions, where the geometric structures of small objects are difficult to capture, while remaining nearly unchanged in far regions to avoid unnecessary computational cost. Importantly, RSV is architecture-agnostic and can directly replace the discretization module in any voxel-based detector without modifying the backbone, network design, or training pipeline. Extensive experiments on the KITTI and nuScenes datasets demonstrate that integrating our RSV into several voxel-based baselines consistently enhances small-object detection performance, especially for the Pedestrian and Cyclist categories, while incurring only marginal additional computational overhead.

Deep Learning · Attention Mechanisms

QIUHAO Zeng, Jerry Huang, Peng Lu, Ruiyi Fang, Gezheng Xu, Zihao Jing, Yufei Cui, Charles X. Ling, Gang Niu, Boyu Wang

Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computation. Management techniques, such as selective token eviction and pruning, have vastly mitigated the issues that have arisen, but often discard potentially useful information to manage the growing memory requirements of the cache. In this paper, we build upon these approaches to propose Attention with Routed Memory ARM, a novel KV caching structure that introduces a fully differentiable, fixed-size memory system organized as a hierarchical routing structure that learns to select memory slots via Gumbel-Softmax and performs sigmoid-gated updates that softly combine new and stored information, avoiding hard eviction and thereby reducing information loss. By combining this with a policy to dynamically select varying amounts of memory at inference, ARM adapts its accesses for simple contexts and expanding retrieval for inputs that require deeper reasoning, enabling more scalable and effective retrieval on both short and long contexts. Experimental results on standard commonsense and long-context reasoning benchmarks demonstrate that ARM achieves superior performance and efficiency compared to fixed KV-caching approaches, while remaining efficient and scalable in terms of both memory and generation latency.

Deep Learning · Attention Mechanisms

Rahul Vashisht, Harish Ramaswamy

A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions. Collapsed and factorized parameterizations of the query-key and output-value circuits lead to qualitatively different attention patterns. In particular, some parameterizations give sharper attention to task-relevant tokens, at a similar training loss. We analyze how the parameterizations of these circuits shape the parameter trajectories in single-layer self-attention models trained on next-token prediction. Through gradient-flow analysis, we show that factorization induces implicit rescaling of the two circuits' learning rates. We derive closed-form dynamics showing that output-value and query-key parameters move along a line, with relative speeds determined by their learning rates. Faster query-key learning relative to output-value learning thus produces sharper attention, as the model compensates for slower output-value learning by increasing attention mass on relevant tokens. Experiments show that differences in the relative learning rates of the two circuits govern attention concentration. This improves attention interpretability while maintaining comparable predictive performance.