论文检索

Deep Learning · Foundation Models

Yiming Liu, Chunyu Wei, haozhe lin, Fengjun Xiao, Junqi Zhang, Yunhai Wang, Yueguo Chen

Relational Deep Learning aims to learn directly on multi-table databases, yet current methods face a fundamental tension: Transformers' quadratic complexity prohibits the large contexts relational data demands, while GNNs sacrifice global context for efficiency. We introduce Ramba, the first selective state-space model for relational databases. Our approach features two innovations: (1) Topology-Aware Linearization, which processes cells via global columnar serialization in O(L) complexity while recovering relational structure through sparse entity and foreign-key attention masks; and (2) Schema Dynamic Gating, which modulates SSM state transitions based on semantic alignment between the currently scanned attribute and the prediction target, enabling cross-table relevance filtering without relying on value distributions. Together, these enable Ramba to ingest vast relational contexts while selectively retaining semantically relevant information, a combination existing architectures cannot achieve. Experiments demonstrate state-of-the-art performance with linear scalability across diverse relational benchmarks.

Deep Learning · Large Language Models

Yee Hin Chong, Jiaming Wu, Youhui Zhang, Peng Qu

Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planning across generations. However, how planning decisions attribute and combine heterogeneous feedback signals remains opaque. Standard end-to-end ablations fail to resolve this question, as iterative planning amplifies early perturbations and conflates feedback effects with trajectory-dependent drift. We introduce CUDAnalyst, a unified analysis layer for controlled, generation-level attribution of planning decisions to feedback components via trajectory freezing and selective feedback injection. CUDAnalyst enables stable generation-level evaluation and principled coalitional-style attribution of feedback effects and interactions. Our results show that explicit planning is beneficial only when feedback is aligned, that effective planning emerges from structured multi-feedback interactions, and that high-level plans from stronger reasoning models can partially transfer to weaker ones. These trends hold across representative workloads and reference induction regimes, indicating that the identified feedback-to-plan structure is robust within the controlled axes studied.

Reinforcement Learning · Deep RL

Zhan Su, Peixi Peng, Xinyu Hu, Cong Li, Yisen Zhao, Zhuojian Li, Yonghong Tian, Fanqi Shen

Most reinforcement learning (RL) baselines maximize future cumulative rewards with a fixed single discount factor, which limits their performance in complex sequential decision-making tasks due to a failure to balance short-term objectives and long-term planning. To address this issue, this paper focuses on a multi-timescale critic framework, where each component corresponds to a Q-value with a distinct discount factor. Two key improvements are proposed: (1) A Neural Reward Decoder reconstructs the reward sequence from multi-scale Q-values, with value and reward reconstruction losses enhancing Q-value estimation consistency; (2) A cross-attention-based Q-weight predictor adaptively adjusts Q-value weights via current observations to generate the final Q-value for policy optimization. Extensive experiments on DMControl and CARLA benchmarks demonstrate that our method significantly outperforms state-of-the-art (SOTA) baselines. Furthermore, we validate the framework's generalizability by integrating it with both off-policy (SAC, DrQ-v2) and on-policy (PPO) algorithms, achieving consistent performance gains. The code is available in the supplementary material.

Reinforcement Learning · Deep RL

Yanzhe Hu, Yijie Jin, Pengfei Liu, Kai Yu, Zhijie Deng

Diffusion Large Language Models (dLLMs) enable parallel token generation, and their block-wise variants have attracted significant attention. However, existing dLLMs usually exhibit an accuracy–parallelism trade-off, where raising tokens per forward (TPF) via aggressive parallel decoding often degrades task accuracy. To address this, we suggest developing a post-training approach to directly optimize the speed–quality frontier of pre-trained dLLMs. Conceptually, we do not require the model to decode aggressively along all sampling trajectories, but rather to find several highly parallelizable ones that can yield correct results. To this end, we resort to a reinforcement learning paradigm, i.e., LightningRL, to optimize rewards regarding both the final accuracy and inference parallelism. LightningRL follows the Group Relative Policy Optimization (GRPO) framework, with further improvements for dLLMs: 1) stabilized training via per-reward decoupled normalization, 2) token-level negative log-likelihood (NLL) loss on correct trajectories for regularization, and 3) improved training efficiency through dynamic sampling with TPF-aware filtering. Across maths and code tasks, LightningRL consistently advances the Pareto frontier, maintaining competitive accuracy while increasing parallelism to an average TPF of 7.3 (up to 11.10 on MBPP).

Deep Learning · Large Language Models

Antonin Berthon, Nicolás Astorga, Mihaela van der Schaar

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open-problem: fine-tuning and parameter-efficient variants risk catastrophic forgetting, while context-based approaches have limited expressiveness and are constrained by the model's effective context. We explore \textit{skill neologisms}--i.e., soft tokens integrated in the model's vocabulary and optimized to improve capabilities over a specific skill--as a way to selectively extend model capabilities to new skills without weight updates. We first observe that off-the-shelf pre-trained LLMs already demonstrate tokens associated with procedural knowledge. We then show that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.

Reinforcement Learning · Deep RL

Quang Anh PHAM, Tien Mai, Akshat Kumar

Imitation Learning (IL) has demonstrated strong capabilities in learning high-quality policies from expert demonstrations for sequential decision-making tasks. Nonetheless, its effectiveness is significantly constrained in low-expert-data regimes. To mitigate this issue, previous works introduce ``*offline IL with supplementary data*" which augments expert demonstrations with additional, low-cost data generated by suboptimal policies. A prominent framework for this setting is Distribution Correction Estimation (DICE), which estimates the optimal density ratio by solving the dual of a divergence minimization problem between the learned policy and the expert visitation distribution. Despite their theoretical appeal, existing DICE-based methods often require adding a dataset regularizer to the divergence objective, or rely on a strict coverage assumption. These weaknesses limit the capability of DICE-based methods, causing them to be inefficient in some contexts. In this paper, we introduce ReDICE, a new method to address these limitations. ReDICE is derived by formulating an objective under a mixture distribution from the KL divergence between expert and learned policy occupancies. We formally prove that the dual of this formulation is mathematically equivalent to a stable Gumbel regression objective. Furthermore, we introduce a novel policy extraction mechanism that significantly improves performance in practice. Experiments across diverse benchmarks show that ReDICE achieves state-of-the-art results relative to prior offline IL baselines.

Optimization · Zero-order and Black-box Optimization

Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh

Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models, yet their optimization dynamics in deep learning remain underexplored. In this work, we provide an explicit step size condition that exactly captures the (mean-square) linear stability of a family of ZO methods based on the standard two-point estimator. Our characterization reveals a sharp contrast with first-order (FO) methods: whereas FO stability is governed solely by the largest Hessian eigenvalue, mean-square stability of ZO methods depends on the entire Hessian spectrum. Since computing the full Hessian spectrum is infeasible in practical neural network training, we further derive tractable stability bounds that depend only on the largest eigenvalue and the Hessian trace. Empirically, we find that full-batch ZO methods operate at the edge of stability: ZO-GD, ZO-GDM, and ZO-Adam consistently stabilize near the predicted stability boundary across CNNs, ResNets, and Transformers on vision tasks. Our results highlight an implicit regularization effect specific to ZO methods, where large step sizes primarily regularize the Hessian trace, whereas in FO methods they regularize the top eigenvalue.

Deep Learning · Foundation Models

Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun

Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific or even untrained priors. \emph{How can we unlock their potential?} We introduce FMPlug, a plug-in framework that redefines how foundation FMs are used in IPs. FMPlug combines an instance-guided, time-dependent warm-start strategy with a sharp Gaussianity regularization, adding problem-specific guidance while preserving the Gaussian structures. This leads to a significant performance boost across image restoration and scientific IPs. Our results point to a path for making foundation FM models practical, reusable priors for IP solving.

Deep Learning · Large Language Models

Yutong Cheng, Haifeng Chen, Wenchao Yu, Xujiang Zhao, Peng Gao, Wei Cheng

As large language models increasingly serve as autonomous coding agents, code documentation must be optimized for agent comprehension rather than human readability. We frame agent-oriented documentation generation as a black-box optimization problem over the documentation space, where quality is measured solely by downstream code correctness. A central challenge for conventional LLM refinement methods is *output coupling*—program entities are interdependent, and refining the documentation of one entity can invalidate its callers, resulting in a persistent *whack-a-mole* phenomenon during inference-time scaling. We propose DocSearch, a dependency-guided bi-level search framework that systematically exploits test-time feedback. The outer level conducts a priority search over the program-entity dependency DAG, enforcing a callee-before-caller refinement order to prevent downstream interference. The inner level performs a beam search over documentation refinements, using diversified error message sampling from self-generated unit tests to better exploit diagnostic signals and escape local optima. We provide theoretical guarantees of monotonic progress, showing that our worthy condition prevents regression while enabling efficient exploration. On DevEval+, DocSearch achieves a 90.7% solve rate with GPT-4o, outperforming the strongest baseline by 32.6%. Cross-language experiments further demonstrate that optimized documentation transfers effectively to different target programming languages.

Jinbo Wang, Mingze Wang, Jiaqi Zhang, Peng Pei, Wei Wang, Xunliang Cai, Weinan E, Lei Wu

We propose **GradPower**, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector $\boldsymbol{g}=(g\_{i})\_{i}$, GradPower first applies the elementwise `sign-power` transformation: $ \varphi_p(\boldsymbol{g}) = \left({\rm sign}(g\_i)|g\_i|^p\right)\_{i} $ for a fixed $p>0$, and then feeds the transformed gradient into a base optimizer. Notably, GradPower requires only a **single-line code change** and no modifications to the base optimizer’s internal logic, including the hyperparameters. When applied to AdamW (termed **AdamWPower**), GradPower consistently achieves lower terminal loss across diverse architectures (LLaMA, Qwen2MoE), parameter scales (66M to 2B), datasets (C4, OpenWebText), and learning-rate schedules (cosine, warmup-stable-decay). The most pronounced gains are observed when training modern mixture-of-experts models with warmup-stable-decay schedules. GradPower also integrates seamlessly with other state-of-the-art optimizers, such as Muon, yielding further improvements. Finally, we provide theoretical analyses that reveal the underlying mechanism of GradPower and highlight the influence of gradient noise.

General Machine Learning · Data

Serin Kim, Sangam Lee, Dongha Lee

Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring user preferences and contexts. To address this challenge, we present Persona2Web, the first benchmark for evaluating personalized web agents on the real open web, built upon the clarify-to-personalize principle, which requires agents to resolve ambiguity based on user history rather than relying on explicit instructions. Persona2Web consists of: (1) user histories that reveal preferences implicitly over long time spans, (2) ambiguous queries that require agents to infer implicit user preferences, and (3) a reasoning-aware evaluation framework that enables fine-grained assessment of personalization. We conduct extensive experiments across various agent architectures, backbone models, history access schemes, and queries with varying ambiguity levels, revealing key challenges in personalized web agent behavior. For reproducibility, our codes and datasets are publicly available at https://anonymous.4open.science/r/Persona2Web-73E8

Deep Learning · Generative Models and Autoencoders

Shuchen Xue, Tianyu Xie, Tianyang Hu, Zijin Feng, Jiacheng Sun, Kenji Kawaguchi, Zhenguo Li, Zhi-Ming Ma

Efficiently scaling Large Language Models (LLMs) necessitates exploring alternatives to dominant autoregressive (AR) methods, with Masked Diffusion Models (MDMs) emerging as candidates. However, comparing AR (typically decoder-only) and MDM (often encoder-only) paradigms is confounded by differing architectures, obscuring true algorithmic and efficiency trade-offs. This research decouples these factors by evaluating MDMs within a decoder-only framework to: (1) Equitably compare MDM (as Any-Order AR) and standard AR paradigms through discrepancies on orders. (2) Investigate MDM architectural impacts on computational efficiency. We show decoder-only MDMs, despite a larger modeling space, can achieve significant inference speedups ($\sim25\times$) and comparable perplexity with techniques like temperature annealing, offering a path to reduced inference compute. This work provides insights for developing more computationally efficient foundation models by disentangling core modeling choices from architectural influences.

Reinforcement Learning · Deep RL

Yunzhe Qi, Sirui Chen, Jiaru Zou, Jingrui He

Effective demonstration selection is crucial for maximizing large language model (LLM) performance in few-shot in-context learning. Due to influences such as recency bias, the effectiveness of demonstrations depends heavily on their context relationship to the specific query, and on the ordering in which they are presented, making demonstration selection a complex combinatorial problem. To address these two challenges, we introduce AutoSelect, a novel framework that formulates demonstration selection as an auto-regressive sequential decision process. At each step, AutoSelect embeds the query and previously selected demonstrations into matrix representations to preserve structural information, and a trainable policy model sequentially selects the next best exemplar. To navigate the factorial space of demonstration permutations, our framework formulates a Kullback-Leibler (KL) regularized optimization problem, from which an optimal policy induces an optimal Plackett-Luce (PL) ranking over all possible demonstration sequences. We prove that minimizing a tractable policy-level Cross-Entropy (CE) loss provably bounds the worst-case discrepancy between our policy's induced PL ranking and the optimal one, enabling tractable prioritization of high-quality sequences. Empirically, AutoSelect outperforms existing heuristic and learning-based methods across nine diverse datasets, achieving up to an 11\% improvement over the strongest baseline. Our results are further supported by analytical studies and a case study, highlighting AutoSelect's key properties, as well as its transferability and generalizability.

Applications · Health / Medicine

heng rao, Jason Zhang, Yu Gu, Zhenghao Liu, Ge Yu, Jeffrey Su, Yang Cao, Fan Yang, Minghan Chen

Predicting long-horizon trajectories of biological dynamical systems remains challenging due to substantial system heterogeneity. Most existing machine learning approaches are system-specific, requiring retraining for each new system and exhibiting limited generalization across distinct biological regimes. To address this limitation, we create a large-scale benchmark of over 1,000 ODE-based systems biology models spanning diverse organisms, biological processes, and dynamical behaviors. Building on this benchmark, we propose a regime-aware trajectory prediction framework that enables cross-system generalization and uncertainty quantification for unseen systems. Our approach introduces structured initial states derived from biological regime priors, such as growth trends and oscillatory rhythms, into conditional flow matching, replacing the standard Gaussian source distribution. We provide theoretical justification for this initialization and empirically demonstrate state-of-the-art accuracy (31\% MAE reduction), well-calibrated uncertainty (17\% CRPS improvement), and efficient long-horizon inference across the benchmark.

Deep Learning · Generative Models and Autoencoders

Paul Caucheteux, Clément Bonet, Anna Korba

Many modern generative models can be viewed as minimizing divergences between probability distributions, yet they rely on different algorithmic and geometric principles. Wasserstein gradient flows provide a continuous-time formulation for optimizing over distributions, and can be approximated through their implicit discretization via the Jordan–Kinderlehrer–Otto (JKO) scheme. In this work, we present a unified theoretical framework for generative modeling based on Wasserstein gradient flows, which we refer to as Generative Wasserstein Flows. We show that a broad class of existing methods can be derived as instances of parametric JKO schemes for f-divergences objectives, and we establish equivalences between several recently proposed algorithms. We extend this framework beyond f-divergences to integral probability metrics, deriving new JKO-based generative algorithms for objectives such as Maximum Mean Discrepancy. We also clarify their connections with GANs. Finally, we analyze parametric Wasserstein flows, where the evolution is restricted to distributions generated by parameterized maps. We characterize the resulting dynamics as projected or preconditioned Wasserstein gradient flows, highlighting the role of the Wasserstein geometry in shaping the learning dynamics of generative models.

Reinforcement Learning · Batch/Offline

Ying Ba, Tianyu Zhang, Mohan Zhou, Yalong Bai, Wenyi Mo, Guiwei Zhang, Bing Su, Ji-Rong Wen

Text-to-image generation models have achieved remarkable progress in preference optimization, yet achieving robust alignment across diverse reward models remains a significant challenge. Existing multi-reward fusion approaches rely on weighted summation, which is costly to tune and insufficient for balancing conflicting objectives. More critically, optimization with reward models is highly susceptible to reward hacking, where reward scores increase while the perceived quality of generated images deteriorates. We demonstrate that optimizing against a unified global target under heterogeneous reward upper bounds can induce reward hacking, a risk further exacerbated by the inherent instability of weak reward models. To mitigate this, we propose a Pareto Frontier-Guided Optimal Transport framework. Our method constructs a prompt-specific Pareto frontier and maps dominated samples toward it via distribution-aware optimal transport. Furthermore, we develop both online and offline optimization strategies tailored to diverse reward signal characteristics. To provide a more rigorous assessment, we introduce the Joint Domination Rate (JDR) and Joint Collapse Rate (JCR) as principled metrics to quantify multi-reward synergy and reward hacking. Experimental results show that our approach outperforms strong baselines with an 11\% gain in JDR and achieves a near 80\% win rate in human evaluations.

Applications · Everything Else

Yaohui Han, Rongliang Fu, Yanming Liu, Shuo Ren, Shuai Dong, Yunpeng Wang, Tinghuan Chen, Bei Yu, Tsung-Yi Ho

In the field of integrated circuits, leaf cells are the basic units, serving as the fundamental building blocks (e.g., standard cells) that are widely reused in various VLSI designs, forming the basis for more complex circuits. Therefore, the design quality of leaf cell layouts significantly impacts the PPA (Power, Performance, and Area) of the final VLSI designs. To automatically design leaf cell layouts that are close to expert designs, we propose GenLeaf. GenLeaf first utilizes a supervised, performance-aware embedding model to represent layouts and automatically calculate their similarity scores. Since there are expert-designed layouts but no corresponding scripts, we implement Bayesian optimization to generate a layout-script dataset for LLM training. With subsequent supervised fine-tuning and further preference optimization, GenLeaf can generate leaf cell layouts through scripts whose performance closely resembles that designed by human engineers. Experiment results demonstrate that GenLeaf outperforms expert-designed golden layouts across key performance metrics.

Applications · Everything Else

Zan Gong, Biting Huang, Fei He

Program termination is a fundamental liveness property in software verification. Proving termination of a given program is a formidable challenge due to the undecidability of the problem. In this paper, we propose LIFT, a termination verification framework that leverages LLMs to generate loop bounds within a guess-and-check workflow. LIFT couples this generation with a sound formal validation procedure that both guarantees all reported terminations and refutes invalid loop bounds via violation analysis. Experiments on publicly accessible termination benchmarks show that LIFT significantly outperforms existing termination verification tools.

Applications · Chemistry, Physics, and Earth Sciences

Dongzhe Zheng, Tao Zhong, Christine Allen-Blanchette

In this paper, we study solution operators of physical field equations on geometric meshes from a function-space perspective. We reveal that Hodge orthogonality fundamentally resolves spectral interference by isolating unlearnable topological degrees of freedom from learnable geometric dynamics, enabling an additive approximation confined to structure-preserving subspaces. Building on Hodge theory and operator splitting, we derive a principled operator-level decomposition. The result is a Hybrid Eulerian-Lagrangian architecture with an algebraic-level inductive bias we call Hodge Spectral Duality (HSD). In our framework, we use discrete differential forms to capture topology-dominated components and an orthogonal auxiliary ambient space to represent complex local dynamics. Our method achieves superior accuracy and efficiency on geometric graphs with enhanced fidelity to physical invariants.

Deep Learning · Robustness

Aviv Adler, Jennifer Tang

A central insight in lossless data compression is the close connection between probabilistic next-symbol prediction and efficient sequence compression, whereby predictive models can be combined with classical coding techniques to achieve strong compression performance. Applying this approach with powerful modern learned models, such as LLMs, has been shown to achieve markedly better compression than traditional techniques across a wide range of domains. However, significant practical challenges remain, including model non-determinism, in which a model produces different predictions on different machines despite identical parameters and inputs; such mismatches between the encoder and decoder can lead to complete decoding failure. Probability Matching Interval Coding (PMATIC) was recently introduced as a drop-in framework for mismatch-robust coding and shown to enable reliable compression and decompression in the presence of bounded prediction mismatch (Adler & Tang, 2026). In this work, we present PMATIC+, a generalization of PMATIC that allows the incorporation of tight theoretical results into the design and more flexible parameter optimization, resulting in substantial improvements in compression efficiency and robustness.