论文检索

Deep Learning · Large Language Models

Peng Lai, Yichao Du, Junchao Wu, Weibo Gao, Linan Yue, Longyue Wang, Weihua Luo, Derek F. Wong, Guanhua CHEN

Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challenge. Existing solutions either depend on costly proprietary LLM-as-a-Judge systems or opaque scalar reward models that lack interpretability. Recent works on generative reward models offer a promising alternative, but they remain constrained by static evaluation criteria, fragmented evaluation paradigms, and limited multilingual support. To address these challenges, we introduce MixReward, a large-scale multilingual dataset spanning six domains and 103 languages, containing both pairwise and listwise data, and propose UniRRM, a unified reasoning reward model supporting multiple languages and evaluation paradigms. UniRRM uses a staged reasoning chain to dynamically generate task-generic and instruction-specific criteria, enabling fine-grained, input-adaptive judgments while maintaining consistency across languages. Experiments demonstrate that UniRRM-8B and UniRRM-14B achieve performance close to the state-of-the-art for models of comparable size across multiple benchmarks, and are effective for unseen evaluation paradigms. In addition, ablation studies validate the reliability and effectiveness of UniRRM.

General Machine Learning · Sequential, Network, and Time Series Modeling

Wanfeng Lu, He Ma, Wei Lin, Qunxi Zhu

Precise prediction of spatiotemporal dynamics over predictive horizons is constrained by the computational cost of high-fidelity solvers and the sparsity, noise, and irregularity of data. We introduce MERLIN, a Koopman-based framework that lifts dynamics to the evolution of learned *observation functionals* with near-linear progression, enabling full-field reconstruction at arbitrary resolutions. Theoretically, we develop a functional Koopman theory for PDEs and compensate for the loss of finite-dimensional linear invariance via the Mori–Zwanzig formalism, which augments the linear backbone with non-Markovian memory terms to improve predictive accuracy. Practically, MERLIN employs discretization-invariant *function encoders* that map partial, irregular observations to observables, and resolution-free *function decoders* that reconstruct states at arbitrary query points. Training under linear constraints yields an interpretable, low-dimensional model that captures principal modes, supports reduced-order modeling, and—augmented with memory correction—delivers stable long-horizon rollouts even in ultra-low-dimensional latent spaces.

General Machine Learning · Evaluation

Medhasweta Sen, Zachary Gottesman, Jiaxing Qiu, C. Bayan Bruss, Nam Nguyen, Thomas Hartvigsen

Recent works propose complex multi-modal models that handle both time series and language, ultimately claiming high performance on complex tasks like time series reasoning and cross-modal question answering. However, they skip foundational evaluations that such complex models should have mastered. So we ask a simple question: $\textit{How well can recent models describe structural properties of time series?}$ To answer this, we propose that successful models should be able to $\textit{recognize}$, $\textit{differentiate}$, and $\textit{generate}$ descriptions of time series. We then create $\textbf{BEDTime}$, a benchmark to assess these novel tasks, that comprises $\textbf{five datasets}$ reformatted across $\textbf{three modalities}$. In evaluating $\textbf{13 state-of-the-art models}$, we find that (1) surprisingly, dedicated time series-language models fall short, despite being designed for similar tasks, (2) vision language models are quite capable, (3) language only methods perform worst, despite many lauding their potential, and (4) all approaches are clearly fragile to a range of real world robustness tests, indicating directions for future work. Together, our findings critique prior works' claims and provide avenues for advancing multi-modal time series modeling.

Deep Learning · Large Language Models

Yuchen Yang, Yaru Zhao, Pu Yang, Shaowei Wang, Zhi-Hua Zhou

While Mixture-of-Experts (MoE) architectures substantially bolster the expressive power of large-language models, their prohibitive memory footprint severely impedes the practical deployment on resource-constrained edge devices, especially when model behavior must be preserved without relying on lossy quantization. In this paper, we present ZipMoE, an efficient and semantically lossless on-device MoE serving system. ZipMoE exploits the synergy between the hardware properties of edge devices and the statistical redundancy inherent to MoE parameters via a caching-scheduling co-design with provable performance guarantee. Fundamentally, our design shifts the paradigm of on-device MoE inference from an I/O-bound bottleneck to a compute-centric workflow that enables efficient parallelization. We implement a prototype of ZipMoE and conduct extensive experiments on representative edge computing platforms using popular open-source MoE models and real-world workloads. Our evaluation reveals that ZipMoE achieves up to 72.77% inference latency reduction and up to $6.76\times$ higher throughput than the state-of-the-art systems. Our code is available at: https://anonymous.4open.science/r/s3fg2i1dn/.

Deep Learning · Attention Mechanisms

Yining Li, Dongchen Han, Zeyu Liu, Hanyi Wang, Yulin Wang, Gao Huang

While linear-complexity attention mechanisms offer a promising alternative to Softmax attention for overcoming the quadratic bottleneck, training such models from scratch remains prohibitively expensive. Inheriting weights from pretrained Transformers provides an appealing shortcut, yet the fundamental representational gap between Softmax and linear attention prevents effective weight transfer. In this work, we address this conversion challenge from two perspectives: architectural alignment and representational alignment. We discover that Test-Time Training (TTT) shares a similar structure with Softmax attention, enabling direct weight inheritance. To further align representational properties— shift-invariance with keys and locality, we introduce instance normalization and locality enhancement module to better approximate the pretrained feature space. We validate our approach by linearizing Stable Diffusion 3.5 and introduce SD3.5-T$^5$. With only 1 hour fine-tuning on 4$\times$H20, SD3.5-T$^5$ achieves a DPG-Bench score of 84.43 (vs.\ 83.83 for the original) while accelerating inference by 1.32$\times$ and 1.47$\times$ at 1K and 2K resolutions.

Deep Learning · Large Language Models

Weihao Liu, Dehai Min, Lu Cheng

While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it requires models to verbalize every intermediate step in text tokens, constraining the model thoughts to the discrete vocabulary space. Recently, reasoning in continuous latent space has emerged as a promising alternative, enabling more robust inference and flexible computation beyond discrete token constraints. However, current latent paradigms often suffer from feature collapse and instability, stemming from distribution mismatches when recurrently using hidden states as the input embeddings, or alignment issues when relying on assistant models. To address this, we propose **Latent Thoughts Tuning (LT-Tuning)**, a framework that redefines how latent thoughts are constructed and deployed. Instead of relying solely on raw hidden states, our method introduces a **Context-Prediction-Fusion** mechanism that jointly leveraging contextual hidden states and predictive semantic guidance from the vocabulary embedding space. Combined with a progressive three-stage curriculum learning pipeline, LT-Tuning also enables dynamically switching between latent and explicit thinking modes. Experiments demonstrate that our method outperforms existing latent reasoning baselines, effectively mitigating feature collapse and achieving robust reasoning accuracy. Code is available at https://anonymous.4open.science/r/LT_Tuning-F35E.

Theory · Learning Theory

Qianqian Lei, Soham Bonnerjee, Yuefeng Han, Wei Biao Wu

While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or sub-Gaussian/sub-Weibull tail assumptions, which can be overly restrictive for modern settings with heavy-tailed or unbounded losses. We develop a stability-based framework that requires only a finite $L_p$ moment condition. Our first contribution is sharp concentration inequalities for functions of independent random variables under $L_p$ constraints, extending McDiarmid's bounded-differences techniques beyond the classical regime. Leveraging these results, we derive sharp high-probability generalization bounds across a range of learning paradigms, including empirical risk minimization, transductive regression, and meta-learning. These guarantees show that $L_p$ stability suffices for robust generalization even when boundedness fails, substantially weakening the standard assumptions in the stability literature.

Social Aspects · Accountability, Transparency, and Interpretability

Lang Gao, Jinghui Zhang, Wei Liu, Fengxian Ji, Chenxi Wang, Zirui Song, Akash Ghosh, Youssef Mohamed, Preslav Nakov, Xiuying Chen

Steering is a widely used technique for controlling large language models, yet its effects are often unstable and hard to predict. Existing theoretical accounts are largely based on the Linear Representation Hypothesis (LRH). While LRH assumes that concepts can be orthogonalized for lossless control, this idealized mapping fails in real representations and cannot account for the observed unpredictability of steering. By relaxing LRH's orthogonality assumption while preserving linear representations, we show that overlapping concept contributions naturally yield a sample-specific axis-orthogonal structure. We formalize this as the Cylindrical Representation Hypothesis (CRH). In CRH, a \textit{\textbf{central axis}} captures the main difference between concept absence and presence and drives concept generation. A \textit{\textbf{surrounding normal plane}} controls steering sensitivity by determining how easily the axis can activate the target concept. Within this plane, only specific \textit{\textbf{sensitive sectors}} strongly facilitate concept activation, while other sectors can suppress or delay it. While the surrounding normal plane can be reliably identified from difference vectors, the sensitive sector cannot, introducing intrinsic uncertainty at the sector level. This uncertainty provides a principled explanation for why steering outcomes often fluctuate even when using well-aligned directions. Our experiments verify the existence of the cylindrical structure and demonstrate that CRH provides a valid and practical way to interpret model steering behavior in real settings: \url{https://anonymous.4open.science/r/CRH}.

Theory · Learning Theory

Sho Sonoda, Shunta Akiyama, Yuya Uezato

Agentic theorem provers---pipelines that couple a mathematical reasoning model with library retrieval, decomposition/search, and a proof assistant verifier---have recently achieved striking empirical success, yet it remains unclear which components drive performance and why such systems work at all despite classical hardness of proof search. We propose a distributional viewpoint and introduce \textbf{statistical provability}, defined as the finite-horizon success probability of reaching a verified proof, averaged over an instance distribution, and formalize modern theorem-proving pipelines as \textbf{time-bounded reachability MDPs}. Exploiting Bellman structure, we prove existence of optimal policies under mild regularity, derive \textbf{provability certificates} via sub-/super-solution inequalities, and bound the performance gap of score-guided planning (greedy/top-\(k\)/beam/rollouts) in terms of approximation error, sequential statistical complexity, representation geometry (metric entropy/doubling structure), and action-gap margin tails. Together, our theory provides a principled, component-sensitive explanation of when and why agentic theorem provers succeed on biased real-world problem distributions, while clarifying limitations in worst-case or adversarial regimes.

Deep Learning · Large Language Models

Jiaqi Wei, Xuehang Guo, Pengfei Yu, Xiang Zhang, Wanli Ouyang, Siqi Sun, Qingyun Wang, Chenyu You

Standard Chain-of-Thought (CoT) reasoning trades reliability for responsiveness: in a single user-visible token stream, more deliberation delays meaningful output, imposing a ``silence tax.'' We introduce \emph{Side-by-Side (SxS) Interleaved Reasoning}, a training framework that makes \emph{disclosure timing} a controllable decision within standard autoregressive generation. By interleaving \emph{supported} partial answers with continued private reasoning in the same context, SxS avoids monolithic reasoning preambles. We treat disclosure as a policy learning problem and train models via a multi-stage pipeline: supervised fine-tuning (SFT) on entailment-aligned interleaved trajectories, followed by reinforcement learning (RL) to recover reasoning performance and optimize accuracy. Without architectural changes, SxS improves the accuracy--latency trade-off across two Qwen3 architectures/scales (MoE \textbf{Qwen3-30B-A3B}, dense \textbf{Qwen3-4B}) and both in-domain (AIME25) and out-of-domain (GPQA-Diamond) benchmarks, reducing \emph{substantive content latency} by 18\% and improving a proxy for perceived wait time by 49\%, yielding more responsive interactions without compromising answer quality.

Reinforcement Learning · Batch/Offline

Jun-Jie Yang, Chia-Heng Hsu, Kui-Yuan Chen, Ping-Chun Hsieh

Preference-based reinforcement learning (PbRL) avoids explicit reward engineering by learning from pairwise human preference feedback. Existing offline PbRL methods typically follow a two-stage pipeline, first learning a reward or preference model from labeled preferences and then performing offline RL on unlabeled data. We revisit offline PbRL through the lens of reward-free representation learning (RFRL) from the zero-shot RL literature, and propose a new training framework that first learns latent successor-measure representations from reward-free offline data, followed by contrastive search and fine-tuning using preference data. Through extensive experiments and ablations, we show that our method achieves superior preference efficiency over offline PbRL baselines. This work is the first to connect RFRL with PbRL, highlighting its potential as a feedback-efficient solution.

Sobhan Lotfi, Ava Iranmanesh, Lachin Naghashyar, Ali Shirali, Fateme Haredasht, Sanmi Koyejo, Phil Torr, Yong Suk Lee, Fazl Barez, Joel Lehman 等

Breakthroughs often come from ideas we could not have predicted in advance. In biology, this is called exaptation: traits evolved for one function become decisive for another. Scientific progress works similarly, but only if ideas survive periods when they appear uncompetitive by current metrics. This position paper argues that AI's benchmark-centered selection environment, while successful at bypassing complex debates about the nature of intelligence, taxes exaptation. When one selection rule dominates, ideas that do not fit it have nowhere to persist. The cost grows acute as the field shifts from asking can machines exhibit intelligent behavior? to asking can machines exhibit intelligent behavior such that they are aligned, interpretable, and safe? These are philosophically distinct questions that may require discoveries that we cannot specify. We propose mechanisms to restore exaptive capacity without abandoning benchmarking: plural evaluation regimes, protected venues for non-comparable work, long-horizon funding, and training norms that encourage researchers to question selection rules, not only optimize within them.

Applications · Everything Else

Yuxuan Liu, Weikai Xu, Kun Huang, Changyu Chen, Jiankun Zhao, Pengzhi Gao, Wei Liu, Jian Luan, Shuo Shang, Bo Du 等

Mobile Agents can autonomously execute user instructions, which requires hybrid-capabilities reasoning, including screen summary, subtask planning, action decision and action function. However, existing agents struggle to achieve both decoupled enhancement and balanced integration of these capabilities. To address these challenges, we propose Channel-of-Mobile-Experts (CoME), a novel agent architecture consisting of four distinct experts, each aligned with a specific reasoning stage, CoME activates the corresponding expert to generate output tokens in each reasoning stage via output-oriented activation. To empower CoME with hybrid-capabilities reasoning, we introduce a progressive training strategy: Expert-FT enables decoupling and enhancement of different experts' capability; Router-FT aligns expert activation with the different reasoning stage; CoT-FT facilitates seamless collaboration and balanced optimization across multiple capabilities. To mitigate error propagation in hybrid-capabilities reasoning, we propose InfoGain-Driven DPO (Info-DPO), which uses information gain to evaluate the contribution of each intermediate step, thereby guiding CoME toward more informative reasoning. Comprehensive experiments show that CoME outperforms dense mobile agents and MoE methods on both AITZ and AMEX datasets

Deep Learning · Large Language Models

Jiaqi Xue, Qian Lou, Jiarong Xing, Heng Huang

As LLMs proliferate with diverse capabilities and costs, LLM routing has emerged by learning to predict each LLM's quality and cost for a given query, then selecting the one with high quality and low cost. However, existing routers implicitly assume a single fixed quality and cost per LLM for each query, ignoring that the same LLM's quality varies with its output length. This causes routers to exclude powerful LLMs when their estimated cost exceeds the budget, missing the opportunity that these LLMs could still deliver high quality at reduced cost with shorter outputs. To address this, we introduce R2-Router, which treats output length budget as a controllable variable and jointly selects the best LLM and length budget, enforcing the budget via length-constrained instructions. This enables R2-Router to discover that a powerful LLM with constrained output can outperform a weaker LLM at comparable cost—efficient configurations invisible to prior methods. Together with the router framework, we construct R2-Bench, the first routing dataset capturing LLM behavior across diverse output length budgets. Experiments show that R2-Router achieves state-of-the-art performance at $4-5\times$ lower cost compared with existing routers. This work opens a new direction: \textit{routing as reasoning}, where routers evolve from reactive selectors to deliberate reasoners that explore which LLM to use and at what cost budget. Source code is available at https://anonymous.4open.science/r/router-763C/README.md, with an interactive demo at https://r2-router.org.

Reinforcement Learning · Deep RL

Paulius Sasnauskas, Yiğit Yalın, Goran Radanovic

We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al., 2023). To address the challenge of reward poisoning attacks targeting the DPT, we propose a novel adversarial training framework, called Adversarially Trained DPT (AT-DPT). Our method simultaneously trains a population of attackers to minimize the true reward of the DPT by poisoning environment rewards, and a DPT model to infer optimal actions from the poisoned data. We evaluate the effectiveness of our approach against standard bandit algorithms, including robust baselines designed to handle reward contamination. Our results show that AT-DPT significantly outperforms them in bandit settings under a learned attacker, and generalizes to more complex environments such as adaptive attackers and MDPs. It shows promise in ICRL as a meta-RL approach to learning effective corruption-robust algorithms.

Deep Learning · Other Representation Learning

Stefanos Pertigkiozoglou, Mircea Petrache, Shubhendu Trivedi, Kostas Daniilidis

Equivariant neural networks exploit underlying task symmetries to improve generalization, but strict equivariance constraints can induce more complex optimization dynamics that can hinder learning. Prior work addresses these limitations by relaxing strict equivariance during training, but typically relies on prespecified, explicit, or implicit target levels of relaxation for each network layer, which are task-dependent and costly to tune. We propose Recurrent Equivariant Constraint Modulation (RECM), a layer-wise constraint modulation mechanism that learns appropriate relaxation levels solely from the training signal and the symmetry properties of each layer's input-target distribution, without requiring any prior knowledge about the task-dependent target relaxation level. We demonstrate that under the proposed RECM update, the relaxation level of each layer provably converges to a value upper-bounded by its symmetry gap, namely the degree to which its input-target distribution deviates from exact symmetry. Consequently, layers processing symmetric distributions recover full equivariance, while those with approximate symmetries retain sufficient flexibility to learn non-symmetric solutions when warranted by the data. Empirically, RECM outperforms prior methods across diverse exact and approximate equivariant tasks, including the challenging molecular conformer generation on the GEOM-Drugs dataset.

Deep Learning · Large Language Models

Felix Parker, Nimeesha Chan, Chi Zhang, Kimia Ghobadi

Time series data is fundamental to decision-making across many domains including healthcare, finance, power systems, and logistics. However, analyzing this data correctly often requires incorporating unstructured contextual information, answering domain-specific questions, and generating natural language explanations – capabilities that traditional time series models lack. While Large Language Models (LLMs) excel at contextual reasoning and knowledge integration, they struggle with numerical time series due to inefficient text-based representations and limited exposure to numerical data during pretraining. We address this gap by augmenting an LLM with specialized time series perception through a patch-based encoder-decoder architecture. We train this Time Series-augmented LLM (TsLLM) on a large corpus of over 20 billion tokens of interleaved time series and text spanning diverse tasks: forecasting with contextual information, question-answering, anomaly detection, classification, report generation, and more, all unified as next token prediction. This training enables TsLLM to leverage both its language understanding and newly acquired temporal reasoning capabilities. While not designed to surpass specialized models on traditional benchmarks, TsLLM demonstrates strong performance on tasks requiring the integration of time series analysis with natural language – capabilities that existing approaches cannot provide. It also exhibits strong zero-shot and few-shot performance, showing it can adapt to new data without additional training.

Stella Biderman, Mohammad Aflah Khan, Niloofar Mireshghallah, Catherine Arnett, Fazl Barez, Naomi Saphra

What would it mean to have a *scientific* understanding of AI? Language models are not static objects—they are snapshots of time-evolving processes shaped by data, objectives, and optimization dynamics. Yet the field predominantly treats models as fixed artifacts, analyzing behaviors after training rather than asking *why* they emerge. **This position paper argues that AI research should move beyond *post hoc* fixes and study the learning dynamics of models.** We envision a hierarchy of scientific maturity: first *predict* outcomes from early training signals, then *intervene* when trajectories go wrong, ultimately *design* training procedures that guarantee desired properties. Scaling laws have reached the first level for loss; the challenge is extending all three levels to general capabilities, biases, and safety. We articulate requirements for such theories, survey progress across mechanistic interpretability, fairness, memorization, and learning dynamics, and identify concrete open problems. The path forward requires treating models as processes to be understood, not just artifacts to be patched.

Applications · Chemistry, Physics, and Earth Sciences

Aleix Segui, Wesley Armour

In AI for Science, physics-informed losses are becoming popular to train learned compressors, but their rate-distortion consequences are poorly understood. We formalise this problem via a geometric framework, showing that physics-aware compression is governed by the interaction of two Riemannian structures in latent space: a Hessian-based physics sensitivity geometry induced by the physical observable, and a rate geometry induced by the entropy model. This theoretical view yields an explicit mechanism for error allocation: the codec concentrates precision along spectrally stiff and rate-expensive directions, while pushing uncertainty into directions that are weakly sensed by the physical observable. We prove fundamental limits from this alignment: (i) rate-efficient preservation is theoretically possible only when physical sensitivity is strongly anisotropic, and (ii) when physics and fidelity are not spectrally aligned, improving physical observables at fixed rate provably worsens standard distortion. We validate these predictions across chaotic fluid dynamics simulations, and introduce simple geometric alignment diagnostics that anticipate when physics-aligned training will succeed.

Applications · Computer Vision

Shuo Cao, Jiayang Li, Xiaohui Li, Yuandong Pu, Kaiwen Zhu, Yuanting Gao, Siqi Luo, Yi Xin, Qi Qin, Yu Zhou 等

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines perceptual-level image understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding.