论文检索

Applications · Neuroscience, Cognitive Science

Kaiwei Che, Wei Fang, Zhengyu Ma, Yifan Huang, Peng Xue, Li Yuan, Yonghong Tian

Spiking Neural Networks (SNNs), with their event-driven and biologically inspired mechanisms, are well-suited for energy-efficient neuromorphic hardware. Neural coding, which is critical to SNNs, determines how information is represented via spikes. While Time-to-First-Spike (TTFS) coding uses a single spike per neuron to offer extreme sparsity and energy efficiency, it often suffers from unstable training and low accuracy due to its sparse firing. To address these challenges, we propose a training framework that incorporates parameter initialization, training normalization, a temporal output decoder, and a re-evaluation of the pooling layer. The proposed parameter initialization and training normalization mitigate signal diminishing and gradient vanishing, which helps stabilize training. Our output decoder aggregates temporal spikes to encourage earlier firing, thereby reducing latency. The re-evaluation of the pooling layer demonstrates that max-pooling violates single-spike constraints, which should be avoided, whereas average-pooling preserves them. Experiments show that our framework stabilizes and accelerates training, reduces latency, and achieves state-of-the-art accuracy for step-by-step TTFS SNNs on MNIST ($99.48\%$), Fashion-MNIST ($92.90\%$), CIFAR10 ($90.56\%$), CIFAR100 ($70.27\%$) and DVS Gesture ($95.83\%$).

Theory · Probabilistic Methods

Yang Yang, Duo Zheng, Sandeep Jain, Kai Zhang, Ping-Shou Zhong

This paper introduces a new family of adaptive, distribution-free independence tests for multivariate random vectors based on binary expansion coefficients, supported by a tractable asymptotic theory. Our first key contribution establishes a general equivalence between independence testing and testing cross-covariances among exponentially many binary expansion interaction coefficients, applicable to broad sample spaces and not limited to kernel-induced representations. While this exponential interaction structure makes naive construction and computation infeasible, we overcome this challenge by reformulating the proposed tests as a class of U-statistics and deriving an explicit kernel representation that enables scalable and efficient computation. Exploiting the multiscale nature of binary expansions, the proposed framework automatically adapts to unknown dependence structures by selectively truncating higher-order interactions, yielding both strong power and clear interpretability. To further enhance power and computational efficiency, we introduce an adaptive weighted aggregation procedure, termed wa-dCoBET, which combines a baseline Covariance Binary Expansion Test (CoBET) with a distance-measure–based CoBET. Extensive simulations and a real-data application demonstrate that wa-dCoBET consistently matches or outperforms HSIC and distance covariance, particularly in higher-dimensional and non-monotone settings, while maintaining accurate type I error control.

Applications · Language, Speech and Dialog

Xiang Li, Pin-Yu Chen, Wenqi Wei

Recent advances in audio deepfake detection have been driven by increasingly large speech foundation models and growing amounts of synthetic data. Despite steady improvements on different benchmarks, it remains unclear how detection performance scales with model capacity and training data under realistic deployment conditions, where detectors operate under distribution shift, signal corruption, and unseen synthesis pipelines. In this work, we present the first systematic study of scaling laws in post-training audio deepfake detection, focusing on fine-tuning regimes rather than large-scale pretraining. Using a controlled family of speech foundation models with shared architecture and pretraining, we analyze how detection performance, robustness, and generalization evolve as a function of model size and training data scale. Our evaluation covers multiple dimensions, including out-of-distribution datasets, common audio corruptions, cross-language generalization, and cross-TTS (Text-to-Speech) generalization to unseen speech synthesis systems. Across settings, we observe consistent but highly non-uniform scaling behavior: while larger models are more sample-efficient and generalize better overall, scaling benefits weaken under corruptions and linguistic shift, and persistent error gaps remain even at the largest scales. Our results reveal a fundamental asymmetry between performance scaling and robustness scaling in audio deepfake detection. While larger detectors consistently improve in-distribution detection performance, gains in robustness and generalization, particularly under cross-language and cross-TTS evaluation, are substantially weaker and exhibit persistent error gaps.

General Machine Learning · Transfer, Multitask and Meta-learning

Nghia Nguyen, Trung Hieu Nguyen, Ang Li, Hoang Pham, Viet Anh Nguyen, Khoa Doan

The intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which interferes with remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches often retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigates an unexplored direction for CL called Retrospective Feature Estimation (RFE). RFE learns to reverse feature changes by aligning the features from the current trained DNN backward to the feature space of the old task, where performing predictions is easier. This retrospective process utilizes a chain of small feature mapping networks called retrospector modules. Empirical experiments on several CL benchmarks, including CIFAR10, CIFAR100, and Tiny ImageNet, demonstrate the effectiveness and potential of this novel CL direction compared to existing representative CL methods, motivating further research into retrospective mechanisms as a principled alternative for mitigating catastrophic forgetting in CL. Code is available at: https://github.com/mail-research/retrospective-feature-estimation.

Social Aspects · Accountability, Transparency, and Interpretability

Belinda Mo

AI systems are becoming autonomous research agents that generate hypotheses, design experiments, and produce discoveries at scales beyond human oversight. As seen by increased submissions to ML venues, the verification gap between scientific output and our ability to check it is already widening, and autonomous agents make it worse by magnitudes given human-agent asymmetry. We argue that science must evolve its verification infrastructure, as it has before with peer review. However, while historical adaptations assumed human contributors who could be questioned and sanctioned, AI agents break this assumption. We propose criteria for an adapted verification infrastructure that emphasizes observable-by-default workflows, scalable verification, and clear attribution. We argue that without adaptation, ML and any scientific domain using agents face dangerous failures: experimental results that no person can verify, optimization for metrics over understanding, and accountability vacuums that erode scientific trust.

Deep Learning · Large Language Models

Truong Nguyen, Tien-Phat Nguyen, Linh Van, Duy Nguyen, Khoa Doan, Trung Le

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions. Existing token-level extensions typically decompose a sequence-level Bradley–Terry objective across timesteps, leaving per-prefix (state-wise) optimality implicit. We study how to recover **token-level** preference optimality using only standard sequence-level pairwise comparisons. We introduce **Token-level Bregman Preference Optimization (TBPO)**, which posits a token-level Bradley--Terry preference model over next-token actions conditioned on the prefix, and derive a Bregman-divergence density-ratio matching objective that generalizes the logistic/DPO loss while preserving the optimal policy induced by the token-level model and maintaining DPO-like simplicity. We introduce two instantiations: TBPO-Q, which explicitly learns a lightweight state baseline, and TBPO-A, which removes the baseline through advantage normalization. Across instruction following, helpfulness/harmlessness, and summarization, TBPO improves alignment quality and training stability and increases output diversity relative to strong sequence-level and token-level baselines.

Deep Learning · Large Language Models

Tiancheng Zhang, Yulin Chen, Yunfeng Zhao, Shaoyuan Huang, Cheng Zhang, Xiaofei Wang

The surge of large language model (LLM) applications on personal devices imposes massive, bursty workloads on cloud serving infrastructure. While prefill-decode disaggregation improves throughput and scalability, memory-bound decode instances often suffer from persistent load imbalance, as output lengths are unknown when requests arrive at the cloud. To address this, we propose MAPS, a memory-aware predictive scheduling framework tailored for disaggregated LLM serving. MAPS performs device-assisted speculative output-length prediction overlapped with cloud-side prefilling, incurring negligible latency overhead. To handle generation uncertainty, MAPS applies uncertainty-aware calibration to derive output length upper bounds with target coverage, enabling safe scheduling decisions. Building on these bounds, MAPS employs a hierarchical global-local scheduling strategy to mitigate inter-decoder queue buildup and intra-decoder head-of-line blocking. Extensive experiments on two real-world workloads and two LLMs show that MAPS significantly outperforms three state-of-the-art systems, reducing average end-to-end latency by 42.6\% and tail latency by up to 84.8\%.

Theory · Deep Learning

Hang Zhou, Ju-Sheng Hong, Xiucai Ding, Jane-Ling Wang

Regression with functional covariates poses fundamental challenges due to the infinite-dimensional nature of functional data, and its theoretical properties have been studied under specialized frameworks in classical nonparametric statistics. While deep neural networks (DNNs) have demonstrated remarkable empirical success in high-dimensional regression, their theoretical behavior in settings involving infinite-dimensional covariates remains largely unexplored. In this work, we study the theoretical performance of DNN-based estimators for regression problems with functional covariates. We extend existing theoretical techniques, which are developed for finite-dimensional covariates supported on compact sets, to the infinite-dimensional and non-compact functional data setting. Under mild conditions, we show that DNN estimators attain minimax-optimal polynomial rates of convergence for both functional linear models and functional generalized linear models. For fully nonparametric regression with functional covariates, we establish a lower bound on the prediction error, and further discuss the fundamental obstacles inherent to this problem and their connections to existing state-of-the-art methods in the literature.

Applications · Language, Speech and Dialog

Yaochen Han, Ke Fan, Hongxu Jiang, Wanqi Xu, Weiyu Xie, Runhua Zhang, Chenhui Zhu, Yixiang Zhang

High-performance GPU kernels are critical for reducing the exponentially growing computational costs of large language models (LLMs), but their development heavily relies on manual tuning by domain experts. While recent advances in LLM-based approaches show promise for automating kernel generation, they still struggle to achieve both correctness and high performance. This limitation primarily arises from the lack of domain-specific optimization guidance, hindering effective exploration of the optimization space. We propose $\textbf{EGG}$, an $\underline{E}$xpert-$\underline{G}$uided Agent Framework for Kernel $\underline{G}$eneration, which incorporates expert optimization principles to guide LLMs’ decisions. Inspired by expert workflows, we decompose kernel generation into two hierarchical stages: 1) algorithmic structure design, which establishes a high-quality computational structure foundation; 2) hardware-specific tuning, which performs targeted adjustments through parallel mapping, tensor tiling, and memory optimization. This staged decomposition defines explicit optimization objectives, structuring the design space to achieve progressive refinements. To this end, a stage-aware multi-agent collaboration mechanism is designed for inter and intra-stage context management, ensuring stable optimization trajectories. Experiments on KernelBench and real-world workloads show that EGG achieves a $2.13\times$ average speedup over PyTorch, outperforming existing agent-based and RL-based approaches.

Social Aspects · Alignment

Jie Hu, Changyuan Yan, Yu Zheng, Ziqian Wang, Jiaming Zhang

Assistive agents, especially those intended to sup- port Blind and Visually Impaired (BVI) users, require accessibility alignment as a first-class de- sign objective. Despite rapid progress in agen- tic AI, most current systems are designed and evaluated under assumptions that implicitly cen- ter sighted users, leading to systematic failures in assistive scenarios that cannot be addressed by model scaling or post-hoc adaptations alone. Based on an analysis of 778 real-world assistance instances involving BVI users, we show that these failures arise from persistent mismatches between agent capabilities and the accessibility-specific needs, risks, and interaction constraints of visu- ally impaired users. We argue that accessibil- ity should be treated as an alignment problem rather than a peripheral usability concern. To this end, we introduce the notion of accessibility alignment and propose a lifecycle-oriented design pipeline for accessibility-aligned assistive agents, spanning user research, system design, and post- deployment iteration. We conclude that BVI users centered assistive tasks provide a critical stress test for agentic AI and motivate a shift toward more inclusive agent design.

Deep Learning · Large Language Models

Siyuan Li, Youyuan Zhang, Fangming Liu, Jing Li

Online model editing for multimodal large language models (MLLMs) requires assimilating a stream of corrections under tight compute and memory budgets. Yet editors developed for text-only LLMs often degrade on MLLMs: visually dominant activations skew the statistics that shape updates, causing *cross-modal conflict*, while sequential writes become entangled in a shared edit space and amplify long-horizon interference, causing *inter-edit interference*. To address these, we propose **M-ORE**, a modality-decoupled online recursive editor for lifelong MLLM adaptation. M-ORE is derived from a unified proximal-projection formulation and admits a closed-form update with a Sherman-Morrison recursion, yielding constant per-edit overhead. It maintains module-wise locality statistics for the text stack and the visual projector to avoid visually dominated update shaping and performs continual updates in a fixed orthogonal low-rank edit subspace via a Sherman-Morrison recursion to mitigate long-horizon interference. Experiments on multiple MLLM backbones and online editing benchmarks show that our M-ORE method consistently improves reliability, generality, and locality over strong baselines, while achieving favorable quality-efficiency scaling.

Applications · Health / Medicine

Nikita Makarov, Maria Bordukova, Lena von Voithenberg, Estrella Pivel-Villanueva, Sabrina Mielke, Jonathan Wickes, Hanchen Wang, Mingyu Ma, Keunwoo Choi, Kyunghyun Cho 等

Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting errors, achieving a median Mean Absolute Scaled Error (MASE) of 0.87 compared to 0.97 for the strongest time-series baseline ($p<0.001$). Furthermore, GDT improves risk stratification, achieving an average concordance index (C-index) of 0.703 across survival, progression, and therapy switching tasks, surpassing the best baseline of 0.662. GDT also generalizes to out-of-distribution clinical trials, matching trained baselines at zero-shot and surpassing them with fine-tuning, achieving a median MASE of 0.75–0.88 and outperforming the strongest baseline in event prediction with an average C-index of 0.672 versus 0.648. Finally, TwinWeaver enables an interpretable clinical reasoning extension, providing a scalable and transparent foundation for longitudinal clinical modeling.

Applications · Health / Medicine

Yuhan Wang, Yuanyuan Zou, Jie Cheng, Bin Dai, Jinhong Guo

Accurately capturing local variations in long series has always been one of the most challenging problems in time-series forecasting especially in medical signals, where local variations often indicate pathological events. Our study reveals a previously overlooked key bottleneck in this field: traditional global and local branches learn similar representations, leading to strong feature coupling and reduced sensitivity to local variations. To address this challenge, we propose the novel Dual-Stream Enhancement Mechanism, which structurally enlarges the difference between global and local patterns, enabling weak interactions between the two. Based on this idea, we introduce a new baseline model for blood glucose prediction: Dual-Stream Enhancement Network (DSENet), which fundamentally alleviates the problem of excessively strong coupling between global and local features. Experimental results show that our model achieves SOTA performance on multiple public datasets. Moreover, benefiting from extremely low computational cost, our model demonstrates strong application potential and can serve as a baseline model in multiple domains in the future.

Reinforcement Learning · Policy Search

Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada, Tadashi Kozuno, Toshinori Kitamura, Shin Ishii, Yutaka Matsuo

In reinforcement learning (RL), agents benefit from exploration *only* because they repeatedly encounter similar states: trying different actions can improve performance or reduce uncertainty; without such retries, a greedy policy is optimal. We formalize this intuition with **ReMax**, an objective that evaluates a policy by the expected maximum return over $M$ samples ($M \in \mathbb{N}$), while accounting for return uncertainty. Optimizing this objective induces stochastic exploration as an emergent property, without explicit bonus terms. For efficient policy optimization, we derive a new policy-gradient formulation for ReMax and introduce **Re**Max **PPO** (**RePPO**), a PPO variant that optimizes ReMax while generalizing the discrete retry count $M$ to a continuous parameter $m > 0$, enabling fine-grained control of exploration. Empirically, RePPO promotes exploration—without any explicit exploration bonuses—on the MinAtar and Craftax benchmarks.

Deep Learning · Large Language Models

Anthony Liang, Jonathan Berant, Adam Fisch, Abhimanyu Goyal, Kalpesh Krishna, Jacob Eisenstein

Reasoning models often spend a lot of time thinking before they generate a visible response. This creates a frustrating, but unfortunately common, experience: the user's time is wasted while the model reasons from a false premise that could have easily been corrected. In contrast, human speakers perform lightweight, incremental check-ins to ensure that conversational participants stay on common ground. With this motivation, we propose \textit{interleaved reasoning} (IR), in which the model alternates between thinking and surfacing intermediate responses, as an alternative to the standard ``think-then-answer'' approach. By providing useful information to the user earlier, IR reduces perceived latency, the time a user waits for an initial output, without compromising the quality of the final response. We focus on a specialization of interleaved reasoning, \method (\textul{Plan}-\textul{T}hought-\textul{A}nswer \textul{In}terleaving), where the first intermediate response is an explicit, step-by-step \textit{plan} for executing the task. This plan-first strategy allows for user intervention and early feedback for subsequent reasoning steps. \method\ yields an $\sim$6\% improvement in pass@1 across several challenging math reasoning and coding benchmarks, while reducing time-to-first-response by over 60\% relative to think-then-answer baselines.

Applications · Health / Medicine

Erjian Zhang, Yatong Hao, Liejun Wang, Zhiqing Guo

While multi-task learning based automatic radiology report generation (RRG) is widely adopted to ensure clinical consistency, most focus on architectural designs yet remain limited to coarse linear scalarization strategies. These strategies can not effectively balance the hard constraints of discriminative clinical supervision with the smoothness requirements of report generation. To address these problems, we analyze the failure mechanism of linear scalarization from the perspective of gradient dynamics for the first time, utilizing the stochastic differential equation (SDE) framework to formalize it as a "Double Dilemma'' of drift term deviation and diffusion term decay. Based on this, we propose a backbone-agnostic optimizer named Conflict-Averse Magnitude-Enhanced Gradient Descent (CAME-Grad). Through conflict-averse direction rectification and magnitude-enhanced energy injection, the algorithm not only ensures geometric validity, but also avoids the local optimal solution. Then, the adaptive gradient fusion technology is used to establish a dynamic balance between the theoretical optimal direction and the task-specific inductive bias. Experiments show that as a universal plug-and-play optimizer, CAME-Grad brings substantial and consistent improvements across eight diverse RRG methods, elevating overall clinical efficacy performance by an average of 2.3% on MIMIC-CXR and 1.9% on IU X-Ray. Our code is available at https://anonymous.4open.science/r/CAME-Grad-04A7.

Applications · Health / Medicine

Jiusong Ge, Yingkang Zhan, Wenjie Zhao, Di Zhang, Ke Wang, Jiashuai Liu, Chunze Yang, Chengzu Li, Jian Zhang, Yuxin Dong 等

Traditional whole slide image (WSI) analysis methods typically rely on the multiple instance learning (MIL) paradigm, which extracts patch-level features at high magnification and aggregates them for slide-level prediction. However, such exhaustive patch-level processing is computationally expensive, severely limiting the efficiency and scalability of WSI analysis. To address this challenge, we propose \textbf{PathCTM} (a \textbf{\ul{Path}}ology-oriented \textbf{\ul{C}}ontinuous \textbf{\ul{T}}hought \textbf{\ul{M}}odel) that enables token-efficient scale-space continuous reasoning for gigapixel WSIs. PathCTM formulates diagnostic inference as a dynamic sequential information pursuit. It progressively transitions from low-magnification global to high-magnification local inspection, and adaptively terminates inference when sufficient evidence is gathered to effectively bound decision uncertainty. Specifically, it uses conditional computation for dynamic scale switching with attention-guided region pruning, coupled with confidence-aware early stopping. Extensive experiments demonstrate that compared with state-of-the-art MIL methods, PathCTM reduces the number of required image patches by 95.95\%, shortens inference time by approximately 95.62\%, and improves AUC by an average of 2.3\%. Code is available at \url{https://anonymous.4open.science/r/PathCTM}.

Deep Learning · Large Language Models

Tsung-Han (Patrick) Wu, Mihran Miroyan, David Chan, Trevor Darrell, Narges Norouzi, Joseph E Gonzalez

Real-world applications of Large Reasoning Models (LRMs) often require reasoning about changing prompts or environments. In this work, we evaluate LRM robustness under two realistic dynamic scenarios: interruptions, which test the accuracy of model responses under budget-constrained outputs, and dynamic context, which tests model adaptation to in-flight changes. Across mathematics and programming benchmarks that require long-form reasoning, static evaluations consistently overestimate robustness: even state-of-the-art LRMs, which achieve high accuracy in static settings, can fail unpredictably when interrupted or exposed to changing context, with performance dropping by up to 60\% when updates are introduced late in the reasoning process. Our analysis further reveals several novel failure modes, including reasoning leakage, where models fold the reasoning into their final answer when interrupted; panic, where under time pressure models abandon reasoning entirely and return incorrect answers; and self-doubt, where performance degrades when trying to incorporate updated information.

Deep Learning · Large Language Models

Yiping Wang, Shao-Rong Su, Zhiyuan Zeng, Eva Xu, Liliang Ren, Xinyu Yang, Zeyi Huang, Xuehai He, Luyao Ma, Baolin Peng 等

Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on ensembles of frontier LLMs to achieve new bounds and is a pure inference system that models cannot internalize the evolving strategies. We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time, allowing models to continually learn from their experiences in improving open optimization problems. ThetaEvolve features a single LLM, a large program database for enhanced exploration, batch sampling for higher throughput, lazy penalties to discourage stagnant outputs, and optional reward shaping for stable training signals, etc. ThetaEvolve is the first evolving framework that enable a small open-source model, like DeepSeek-R1-0528-Qwen3-8B, to achieve new best-known bounds on open problems (circle packing and first auto-correlation inequality) mentioned in AlphaEvolve. Besides, across two models and four open tasks, we find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines, and the model indeed learns evolving capabilities, as the RL-trained checkpoints demonstrate faster progress and better final performance on both trained target task and other unseen tasks. We will release our code publicly.

Deep Learning · Large Language Models

Bing Wang, Ximing Li, Changchun Li, Jinjin Chi, Gang Niu, Masashi Sugiyama

Recently, the prominent performance of large language models (LLMs) has been largely driven by multi-task instruct-tuning. Unfortunately, this training paradigm suffers from a key issue, named cross-task interference, due to conflicting gradients over shared parameters among different tasks. Some previous methods mitigate this issue by isolating task-specific parameters, e.g., task-specific neuron selection and mixture-of-experts. In this paper, we empirically reveal that the cross-task interference still exists for the existing solutions because of many parameters also shared by different tasks, and accordingly, we propose a novel solution, namely Basic Abilities Decomposition for multi-task Instruct-Tuning (BADIT). Specifically, we empirically find that certain parameters are consistently co-activated, and that co-activated parameters naturally organize into base groups. This motivates us to analogize that LLMs encode several orthogonal basic abilities, and that any task can be represented as a linear combination of these abilities. Accordingly, we propose BADIT that decomposes LLM parameters into orthogonal high-singular-value LoRA experts representing basic abilities, and dynamically enforces their orthogonality during training via spherical clustering of rank-1 components. We conduct extensive experiments on the SuperNI benchmark with 6 LLMs, and empirical results demonstrate that BADIT can outperform SOTA methods and mitigate the degree of cross-task interference.