论文检索

Deep Learning · Robustness

Alireza Abdollahpourrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard

Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data. Weight-space ensembling methods, such as Model Soups, mitigate this effect by averaging multiple checkpoints, but they are computationally prohibitive, requiring the training and storage of dozens of fine-tuned models. In this paper, we introduce MonoSoup, a simple, data-free, hyperparameter-free, post-hoc method that achieves a strong ID–OOD balance using _only a single_ checkpoint. Our method applies Singular Value Decomposition (SVD) to each layer’s update and decomposes it into high-energy directions that capture task-specific adaptation and low-energy directions that introduce noise but may still encode residual signals useful for robustness. MonoSoup then uses entropy-based effective rank to automatically re-weigh these components with layer-wise coefficients that account for the spectral and geometric structure of the model. Experiments on CLIP models fine-tuned on ImageNet and evaluated under natural distribution shifts, as well as on Qwen language models tested on mathematical reasoning and multiple-choice benchmarks, show that this plug-and-play approach is a practical and effective alternative to multi-checkpoint methods, retaining much of their benefits without their computational overhead.

Probabilistic Methods · Everything Else

Philip Mortimer, Cristiana Diaconu, Tommy Rochussen, Bruno Mlodozeniec, Richard E Turner

Neural Processes (NPs), and specifically Transformer Neural Processes (TNPs), have demonstrated remarkable performance across tasks ranging from spatiotemporal forecasting to tabular data modelling. However, many of these applications are inherently sequential, involving continuous data streams such as real-time sensor readings or database updates. In such settings, models should support cheap, incremental updates rather than recomputing internal representations from scratch for every new observation—a capability existing TNP variants lack. Drawing inspiration from Large Language Models, we introduce the Incremental TNP ($\texttt{incTNP}$). By leveraging causal masking, Key-Value (KV) caching, and a data-efficient autoregressive training strategy, $\texttt{incTNP}$ matches the predictive performance of standard TNPs while reducing the computational cost of updates from quadratic to linear time complexity. We empirically evaluate our model on a range of synthetic and real-world tasks, including tabular regression and temperature prediction. Our results show that, surprisingly, $\texttt{incTNP}$ delivers performance comparable to—or better than—non-causal TNPs while unlocking orders-of-magnitude speedups for sequential inference. Finally, we assess the consistency of the model's updates---by adapting a metric of "implicit Bayesianness", we show that $\texttt{incTNP}$ retains a prediction rule as implicitly Bayesian as standard non-causal TNPs, demonstrating that $\texttt{incTNP}$ achieves the computational benefits of causal masking without sacrificing the consistency required for streaming inference.

General Machine Learning · Representation Learning

Katharina Friedl, Noémie Jaquier, Mika Liao, Danica Kragic

Embedding physical intuition into network architectures allows the learning of dynamics that enforce fundamental properties, such as energy conservation laws, thereby leading to physically-plausible predictions. Yet, scaling these models to intrinsically high-dimensional dynamical systems remains a significant challenge. This paper introduces Reduced-order Hamiltonian Neural Network (RO-HNN), a novel physics-inspired neural network that combines the conservation laws of Hamiltonian mechanics with the scalability of model order reduction. RO-HNN is built on two core components: a novel geometrically-constrained symplectic autoencoder that learns a low-dimensional, structure-preserving symplectic submanifold, and a geometric Hamiltonian neural network that models the dynamics on the submanifold. Our experiments demonstrate that RO-HNN provides physically-consistent, stable, and generalizable predictions of complex high-dimensional dynamics, thereby effectively extending the scope of Hamiltonian neural networks to high-dimensional physical systems.

Deep Learning · Large Language Models

Rulin Shao, Akari Asai, Shannon Shen, Hamish Ivison, Varsha Kishore, Jingming Zhuo, Xinran Zhao, Molly Park, Samuel Finlayson, David Sontag 等

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with **Reinforcement Learning with Evolving Rubrics (RLER)**, where rubrics are constructed and maintained to *co-evolve* with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop **Deep Research Tulu (DR Tulu-8B)**, the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu-8B substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).

Rulin Shao, Akari Asai, Shannon Shen, Hamish Ivison, Varsha Kishore, Jingming Zhuo, Xinran Zhao, Molly Park, Samuel Finlayson, David Sontag 等

Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via reinforcement learning with verifiable rewards, which does not extend to realistic long-form tasks. We address this with **Reinforcement Learning with Evolving Rubrics (RLER)**, where rubrics are constructed and maintained to *co-evolve* with the policy model during training. This allows the rubrics to incorporate newly explored information from search and contrasting model responses, enabling better fact checking and more discriminative on-policy feedback. Using RLER, we develop **Deep Research Tulu (DR Tulu-8B)**, the first fully open model that is directly trained for open-ended, long-form deep research. Across four long-form deep research benchmarks in science, healthcare, and general domains, DR Tulu-8B substantially outperforms existing open deep research agents (by 15.6% over Tongyi DR on average) and matches or exceeds proprietary deep research agents (by 0.7% over OpenAI DR on average), while being significantly smaller and cheaper per query (1000x cheaper than OpenAI DR per query).

Deep Learning · Large Language Models

Chenyi Li, Yanchen Nie, Zhenyu Ming, Gong Zhang, Kun Yuan, Zaiwen Wen

Recent advances in formal theorem proving have focused on Olympiad-level mathematics, leaving undergraduate domains largely unexplored. Optimization, fundamental to machine learning, operations research, and scientific computing, remains underserved by existing provers. Its reliance on domain-specific formalisms (convexity, optimality conditions, and algorithmic analysis) creates significant distribution shift, making naive domain transfer ineffective. We present OptProver, a trained model that achieves robust transfer from Olympiad to undergraduate optimization. Starting from a strong Olympiad-level prover, our pipeline mitigates distribution shift through two key innovations. First, we employ large-scale optimization-focused data curation via expert iteration. Second, we introduce a specialized preference learning objective that integrates perplexity-weighted optimization with a mechanism to penalize valid but non-progressing proof steps. This not only addresses distribution shifts but also guides the search toward efficient trajectories. To enable rigorous evaluation, we construct a novel benchmark in Lean 4 focused on optimization. On this benchmark, OptProver achieves state-of-the-art Pass@1 and Pass@32 among comparably sized models while maintaining competitive performance on general theorem-proving tasks, demonstrating effective domain transfer without catastrophic forgetting.

Deep Learning · Algorithms

Andrei Panferov, Erik Schultheis, Soroush Tabesh, Dan Alistarh

The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs. Yet, existing quantized training methods still sacrifice some of the representation capacity of this format in favor of more accurate unbiased quantized gradient estimation by stochastic rounding (SR), losing noticeable accuracy relative to standard FP16 and FP8 training. In this paper, improve the state of the art for quantized training in NVFP4 via a novel unbiased quantization routine for micro-scaled formats, called MS-EDEN, that has more than 2x lower quantization error than SR. We integrate it into a novel fully-NVFP4 quantization scheme for linear layers, called Clover. We show analytically that Clover achieves consistently better gradient estimation across all major matrix multiplications, both on the forward and on the backward passes. In addition, our proposal synergizes well with recent training improvements aimed specifically at NVFP4. We further validate Clover on end-to-end LLM training with up to 1.9B parameters on 38B tokens. We provide kernels for execution on NVIDIA Blackwell GPUs with up to 4.2x speedup over BF16.

Deep Learning · Algorithms

Hong-Kun Zhang, Xin Li, Sikun Yang, Zhihong Xia

A novel neural network inspired by Cauchy's integral formula, is proposed for function approximation tasks that include time series forecasting, missing data imputation, etc. Hence, the novel neural network is named CauchyNet. By embedding real-valued data into the complex plane, CauchyNet efficiently captures complex temporal dependencies, surpassing traditional real-valued models in both predictive performance and computational efficiency. Grounded in Cauchy's integral formula and supported by the universal approximation theorem, CauchyNet offers strong theoretical guarantees for function approximation. The architecture incorporates complex-valued activation functions, enabling robust learning from incomplete data while maintaining a compact parameter footprint and reducing computational overhead. Through extensive experiments in diverse domains, including transportation, energy consumption, and epidemiological data, CauchyNet consistently outperforms state-of-the-art models in predictive accuracy, often achieving a lower mean absolute error with fewer parameters. These findings highlight CauchyNet’s potential as an effective and efficient tool for data-driven predictive modeling, particularly in resource-constrained and data-scarce environments. The code used to reproduce the results will be released upon the publication.

Deep Learning · Foundation Models

Amir Rezaei Balef, Mykhailo Koshil, Katharina Eggensperger

Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise dynamics in 6 state-of-the-art tabular in-context learning models. We explore how predictions emerge across depth, identify distinct stages of inference and reveal latent-space dynamics that differ from those of language models. Our findings indicate substantial depthwise redundancy across multiple models, suggesting iterative refinement with overlapping computations during inference stages. Guided by these insights, we design a proof-of-concept, looped single-layer model that uses only 20% of the original model’s parameters while achieving comparable performance.

Social Aspects · Accountability, Transparency, and Interpretability

Viet-Hung Tran, Zichi Zhang, Ngoc Doan, Xuan Hoang Nguyen, Phi Nguyen, Yimeng An, Peixin Li, Hans Vandierendonck, Ira Assent, Thai Son Mai

Deep Neural Networks (DNNs) achieve outstanding performance in Time Series Classification (TSC) yet remain opaque "black boxes", hindering their adoption in sensitive domains. While Explainable AI (XAI) aims to bridge this gap, existing TSC XAI methods rely on a single perspective and incur significant computational costs, making them difficult to integrate into real-time applications. To overcome these challenges, we propose a framework, containing two key techniques called Instance-level Multi-Expert Knowledge Distillation (IMEKD) and Semi-Amortized Optimization Explanation (SAOE). Unlike static methods, our IMEKD approach bridges the gap between explanation methods by dynamically selecting the best attribution map from a pool of "XAI experts" for each instance. We then distill this instance-optimal knowledge into a DNN using our SAOE framework, a dual-stage process that learns a global attribution via distillation and refines it using faithfulness and robustness losses, aligning the optimization with objectives of human evaluation. To the best of our knowledge, this is the first work to unify multi-expert selection with semi-amortized optimization for TSC XAI. Also, we introduce a Faithfulness-Preserving Segmentation (FPS) mechanism that converts point-wise maps into interpretable segments without sacrificing fidelity to align explanations with human intuition. Comprehensive experiments on four synthetic datasets, a ECG dataset with human-verified ground truth, and 11 multivariate UEA benchmarks across three DNN architectures show that our framework significantly outperforms the current state-of-the-art (SOTA) in terms of faithfulness, robustness, and computational efficiency.

Deep Learning · Sequential Models, Time series

Longlong Xu, Zeyan Li, Xiao He, Zhaoyang Yu, Changhua Pei, Zhe Xie, Zijun Dou, Tieying Zhang, Dan Pei

Time series forecasting plays a vital role in numerous domains. However, real-world time series are frequently contaminated by noise, missing values, and anomalies, posing significant challenges to reliable forecasting. In this work, we first systematically investigate a fundamental limitation prevalent in existing forecasting methods: an excessive reliance on the most recent observations---termed "recent-data bias". This bias renders forecasts highly vulnerable to perturbations in recent data, severely undermining prediction reliability. To address this issue, we propose TameR, a novel approach for robust time series forecasting that effectively mitigates recent-data bias via enhancing the utilization of global context. Specifically, it employs a basis-aligned randomized sampling strategy to reduce dependence on any specific recent data. Furthermore, TameR incorporates a learnable periodicity extraction module coupled with a two-stage learning protocol to robustly separate periodic patterns from the sampled residual components. Comprehensive experiments demonstrate that TameR significantly outperforms state-of-the-art methods in robustness against diverse perturbation scenarios, while achieving comparable accuracy on clean data.

Deep Learning · Graph Neural Networks

Nicolas Keriven

Oversmoothing has long been identified as a major limitation of Graph Neural Networks (GNNs): input node features are smoothed at each layer and converge to a constant non-informative representation, *if the weights of the GNN are sufficiently bounded*. This assumption is crucial: if, on the contrary, the weights are sufficiently large, then oversmoothing may be compensated. Theoretically, GNN could thus *learn* to not oversmooth. However, this does not really happen in practice, which prompts us to examine oversmoothing from an *optimization* point of view. In this paper, we analyze *backward oversmoothing*, that is, the notion that backpropagated errors are also subject to oversmoothing from output to input. With non-linearities, we outline the key role of the *interaction* between forward and backward smoothing. Moreover, we show that, due to backward oversmoothing, GNNs provably exhibit many *spurious stationary points*: as soon as the *last* layer is trained, the *whole* GNN is at a stationary point. As a result, we can exhibit regions where gradients are near-zero while the loss stays high. Additionally, we prove that this is *specific* to GNNs, and does not necessarily hold for Multi-Layer Perceptrons. This paper is a step toward a more complete comprehension of the optimization landscape of GNNs.

Deep Learning · Sequential Models, Time series

Longlong Xu, Zeyan Li, Xiao He, Zhaoyang Yu, Dazhong Wen, Mingze Sun, Changhua Pei, Dan Pei

Time series foundation models (TSFMs) have demonstrated impressive generalization capabilities across diverse domains. However, they face significant challenges in long-term and ultra long-term forecasting. These challenges primarily arise from scalability limitations when TSFMs process extensive sequence lengths. To address this, we propose SPRINT, a training-free plug-and-play framework designed to empower TSFMs to see more, forecast better and faster during inference. The core idea is to perform forecasting in a downsampled-resolution space, enabling an extended look-back window with reduced computational costs. To avoid information loss and resolution mismatch caused by downsampling, SPRINT decomposes time series into trend and seasonal components, processing them separately. It predicts the low-frequency trend via a Resolution Interpolation workflow within the downsampled space, while preserving high-frequency details through a Pattern Replication mechanism for seasonality. Extensive experiments show that SPRINT achieves a significant improvement, increasing accuracy by 19\% while enhancing efficiency with a reduction of max memory usage by 6.4$\times$ and inference time by 16.9$\times$ compared to state-of-the-art TSFMs.

Social Aspects · Security

Weichen Yu, Ravi Mangal, Yinyi Luo, Kai Hu, Jingxuan He, Corina Pasareanu, Matt Fredrikson

Large Language Models are rapidly becoming core components of modern software development workflows, yet ensuring code security remains challenging. Existing vulnerability detection pipelines either rely on static analyzers or use LLM/GNN-based detectors trained with coarse program-level supervision. Both families often require complete context, provide sparse end-of-completion feedback, and can degrade as code length grows, making them ill-suited for real-time, prefix-level assessment during interactive coding and streaming generation. We propose \textbf{SecCodePRM}, a security-oriented process reward model that assigns a \textbf{context-aware}, \textbf{step-level} security score along a code trajectory. To train the model, we derive step-level supervision labels from static analyzers and expert annotations, allowing the model to attend more precisely to fine-grained regions associated with inter-procedural vulnerabilities. SecCodePRM has three applications: full-code vulnerability detection (VD), partial-code VD, and secure code generation (CG). For VD, SecCodePRM uses risk-sensitive aggregation that emphasizes high-risk steps; for CG, SecCodePRM supports inference-time scaling by ranking candidate continuations and favoring higher cumulative reward. This design yields dense, real-time feedback that scales to long-horizon generation. Empirically, SecCodePRM outperforms prior approaches in all three settings, while preserving code functional correctness, suggesting improved security without a safety–utility tradeoff.

Reinforcement Learning · Online

Chenyi Li, Yuan Zhang, Bo Wang, Guoqing Ma, Wei Tang, Haoyang Huang, Nan Duan

Reinforcement learning with verifiable rewards has shown notable effectiveness in enhancing large language models (LLMs) reasoning performance, especially in mathematics tasks. However, such improvements often come with reduced outcome diversity, where the model concentrates probability mass on a narrow set of solutions. Motivated by diminishing-returns principles, we introduce a set level diversity objective defined over sampled trajectories using kernelized similarity. Our approach derives a leave-one-out marginal contribution for each sampled trajectory and integrates this objective as a plug-in advantage shaping term for policy optimization. We further investigate the contribution of a single trajectory to language model diversity within a distribution perturbation framework. This analysis theoretically confirms a monotonicity property, proving that rarer trajectories yield consistently higher marginal contributions to the global diversity. Extensive experiments across a range of model scales demonstrate the effectiveness of our proposed algorithm, consistently outperforming strong baselines in both Pass@1 and Pass@K across various benchmarks.

Costin-Andrei Oncescu, Qingyang Wu, Wai Tong Chung, Tsai-chuan Wu, Bryan Gopal, Junxiong Wang, Tri Dao, Ben Athiwaratkun

An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subset of them. During autoregressive generation, these models often enter a memory-bound regime even for moderate batch sizes because the average expert load grows more slowly than in an equivalent dense feedforward layer. Consequently, MoE latency is governed by the number of activated experts. We introduce a framework for $\textbf{dynamically}$ re-routing token-to-expert mapping to lower this number (and thus, the decode latency) while preserving a comparable quality. Our best results use a $\textbf{batch-aware routing}$ that works by having tokens $\textbf{piggyback}$ experts that have already been loaded into memory due to being crucial to other tokens within the same batch. Empirically, we evaluate our method on the Qwen3-30B and Qwen3-235B models with a batch size of $16$. Without any statistically significant loss in accuracy, our approach achieves latency reductions of $39\\%$ and $15\\%$ in the MoE layer decode latency, respectively.

Reinforcement Learning · Deep RL

Bhavya Agrawalla, Michal Nauman, Aviral Kumar

Recent work shows that flow-matching networks can be effective for value function estimation in reinforcement learning, but it remains unclear why they work well or whether flow-matching Q-functions differ fundamentally from standard critics. We show that their success is not explained by distributional RL: explicitly modeling return distributions often degrades performance. Instead, we argue that flow-matching Q-functions are effective because they couple a learned velocity field with an integration procedure that is used both during training and to read out Q-values at inference time. This coupling enables robust value prediction through \emph{test-time recovery} from imperfect intermediate estimates where errors dampen out as more integration steps are performed. This mechanism is absent in monolithic critics. Beyond test-time recovery, training with the integration procedure induces more \emph{plastic} representations, allowing critics to represent non-stationary future TD targets without overwriting previous features. We formalize these effects and validate them empirically, showing that flow-matching critics outperform monolithic critics by over $2\times$ in performance and achieve $5$–$10\times$ higher sample efficiency in high-UTD regimes.

Social Aspects · Safety

Jiachen Ma, Jiawen Zhang, Xiangtian Li, Bo Zou, Chaochao Lu, Chao Yang

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation process. To address these vulnerabilities, we propose Reflector, a principled two-stage framework that internalizes self-reflection within the generation trajectory. Reflector first leverages teacher-guided generation to produce high-quality reflection data for supervised fine-tuning (SFT), establishing structured reflection patterns. It subsequently uses Reinforcement Learning (RL) with outcome-driven and reward-validity supervision to instill robust, autonomous self-reflection capabilities. Empirical results show that Reflector achieves Defense Success Rates (DSR) exceeding 90% against complex indirect attacks while generalizing robustly across diverse threat scenarios. Notably, the framework enhances both task-specific and general utility, yielding a 5.85% gain on GSM8K alongside improved performance on knowledge-intensive benchmarks. By internalizing trajectory-level safety, Reflector overcomes the fundamental limitations of surface alignment without significant computational overhead, offering an efficient and scalable solution for the development of safe and capable LLMs.

Deep Learning · Foundation Models

Keondo Park, Younghoon Na, Yourim Choi, Hyunwoo Ryu, Hyun-Woo Shin, Hyung-Sin Kim

While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal context of Polysomnography (PSG) and fail to capture the global macro-structure of a full night's sleep. To address this, we introduce SleepMaMi, a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies. Our framework utilizes a hierarchical dual-encoder design: a Macro-Encoder to model full-night temporal dependencies and a Micro-Encoder to capture short-term characteristics from biosignals. Macro-Encoder is trained via Demographic-Guided Contrastive Learning, which aligns overnight sleep patterns with objective subject metadata, such as age and sex, to refine global representations. Micro-Encoder is optimized via a hybrid Masked Autoencoder (MAE) and multi-modal contrastive objective. Pre-trained on a massive corpus of >20,000 PSG recordings (15.8K hours), SleepMaMi outperforms existing foundation models across a diverse suite of downstream tasks, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.

Social Aspects · Safety

Xiaofei Wen, Wenjie Mo, Yanan Xie, Peng Qi, Muhao Chen

Autonomous web agents are increasingly deployed for long-horizon tasks, yet their ability to adhere to real-world policies remains critically underexplored compared to standard safety objectives. To address this gap, we introduce PolicyGuardBench, a benchmark of 60k policy-trajectory pairs designed to evaluate compliance through both full-trajectory and novel prefix-based violation detection tasks. Using this dataset, we train PolicyGuard, a lightweight guardrail model that achieves strong detection accuracy while maintaining high inference efficiency. Notably, our model demonstrates robust generalization capabilities, preserving high performance even on unseen domains. Together, these contributions establish a comprehensive framework for studying policy compliance, showing that accurate and generalizable guardrails are feasible at small scales.