论文检索

Deep Learning · Large Language Models

Jian Mu, Tianyi Lin, Chengwei Qin, Zhongxiang Dai, Yao Shu

Large language models are increasingly deployed in multi-turn interactive settings where users or environments can iteratively provide lightweight feedback. Unfortunately, optimizing such behavior presents a sharp dilemma in practice: online reinforcement learning is able to effectively address multi-turn dynamics but is prohibitively expensive due to the cost of generating full correction trajectories at every update, whereas offline supervised fine-tuning (SFT) is efficient but suffers from distribution shift and behavioral collapse. To this end, we novelly propose DRIFT (Decoupled Rollouts and Importance-Weighted Fine-Tuning), a framework that operationalizes the theoretical insight that the KL-regularized RL objective is mathematically equivalent to importance-weighted supervised learning. DRIFT decouples rollout from optimization by sampling offline interaction trajectories from a fixed reference policy, deriving return-based importance weights, and optimizing the policy via weighted SFT on the resulting dataset. Empirically, we demonstrate that DRIFT matches or exceeds the performance of multi-turn reinforcement learning baselines while maintaining the training efficiency and simplicity of standard supervised fine-tuning.

Deep Learning · Foundation Models

Tejas Krishnan, Sumeet Motwani, Charles London, Suhaas Bhat, Huitian Jiao, Phil Torr, Riashat Islam, Christopher Summerfield, Christian Schroeder de Witt, Qilong Gu 等

Reinforcement learning with verifiable rewards (RLVR) on foundation models has led to significant improvements in math and code generation. Extending these gains to open-ended domains remains challenging: ground-truth verification is unavailable, human annotation is expensive, and learnt reward models are prone to reward hacking. We introduce Rubric Curriculum RL (RcRL), a self-improvement method for creative short-fiction writing that requires no new data, human annotations, or stronger teacher models. RcRL exploits the generation-verification gap: it is easier to judge whether work is creative than to produce something creative. While this gap exists across open-ended domains, exploiting it for RL is challenging due to reward hacking. During training, we use pairwise preferences against a curriculum of rubric criteria, which provides a more stable signal than absolute scoring while reducing reward hacking against a stationary objective. Unlike baseline methods, which plateau or collapse within a few dozen steps, our approach preserves output entropy and shows improvements over 1000+ training steps. In human evaluations, RcRL-trained models achieve a 70.5% win rate and demonstrate consistent gains across multiple creative writing benchmarks and judges.

Deep Learning · Large Language Models

Pouya Behzadifar, Parshin Shojaee, Sanchit Kabra, Kazem Meidani, Chandan Reddy

Finding mathematical relations underlying natural phenomena is a fundamental task in scientific discovery. Recent advances in evolutionary search with Large Language Models (LLMs) show great promise by leveraging their embedded scientific knowledge. However, discovering governing equations remains challenging due to vast combinatorial hypothesis spaces with exponentially many possible relations. Existing LLM-based approaches treat LLMs as static hypothesis generators unaware of the observed scientific system, leading to suboptimal and inefficient exploration that over-relies on internal priors. To address this, we introduce \emph{Decompose, Adapt, and Evolve} (\textbf{DecAEvolve}), a framework that combines granular feedback from symbolic term decomposition with LLM refinement through reinforcement learning fine-tuning. DecAEvolve unifies symbolic decomposition with test-time RL adaptation, enabling adaptive rather than static hypothesis generation. Our experiments across diverse scientific benchmarks demonstrate that DecAEvolve significantly improves both the accuracy of discovered equations and the efficiency of the discovery process, reducing error by up to an order of magnitude compared to state-of-the-art baselines.

Deep Learning · Generative Models and Autoencoders

Raghav Kansal, David Crair, Nghia Nguyen, Scott Pope, Bradley Parry

Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions. However, less explored is the setting with intermediate observed marginals that can help constrain the flows between the endpoints. This "multimarginal" regime is central to modeling temporal evolution in dynamical systems in many scientific domains that can sample sequential distributions, such as biology and meteorology. We tackle this problem with a novel approach that leverages the connection between FM and dynamic optimal transport (OT), introducing time-dependent potential terms in the dynamic OT action that can steer the flow towards the intermediate marginals. By extending the conditional FM learning target to incorporate these potentials, we derive an efficient, simulation-free algorithm for multimarginal FM that offers considerable flexibility in the spatiotemporal dynamics of the learned flows. We demonstrate state-of-the-art performance of OT-potential FM (OTP-FM) on diverse scientific datasets.

Applications · Neuroscience, Cognitive Science

Louis Schiekiera, Max Zimmer, Christophe Roux, Sebastian Pokutta, Fritz Günther

We investigate the extent to which an LLM’s hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer models, we run two experimental paradigms---similarity-based forced choice and free association---over a shared 5,000-word vocabulary, collecting 17.5M+ trials to build behavior-based similarity matrices. Using representational similarity analysis, we compare behavioral geometries to layerwise hidden-state similarity and benchmark against FastText, BERT, and cross-model consensus. We find that forced-choice behavior aligns substantially more with hidden-state geometry than free association. In a held-out-words regression, behavioral similarity (especially forced choice) predicts unseen hidden-state similarities beyond lexical baselines and cross-model consensus, indicating that behavior-only measurements retain recoverable information about internal semantic geometry. Finally, we discuss implications for the ability of behavioral tasks to uncover hidden cognitive states.

Jacob Bamberger, Adam Gosztolai, Pierre Vandergheynst, Michael Bronstein, Iolo Jones

High-dimensional datasets often concentrate near low-dimensional structures, but estimating their geometry from samples typically relies on graphs and kernels that scale poorly with dataset size and dimension. We propose **Riemannian metric matching**: a denoising probabilistic framework for learning the Riemannian geometry of data using neural networks. Specifically, we learn the *carré du champ* operator, which, using diffusion geometry, gives us access to the Riemannian geometry toolkit for downstream machine learning and statistical tasks. Our key observation is that the carré du champ operator can be formulated as a conditional expectation over random perturbations of the data, which can be exploited for sample-wise training and constant cost, amortized inference without explicit kernel construction. To the best of our knowledge, we provide the first neural surrogate that estimates the underlying Riemannian geometry of data with a provable consistency guarantee in the large data limit. Empirically, metric matching rivals or improves the accuracy of $k$-NN-based diffusion geometry estimators, while enabling amortized inference that is up to $400\times$ faster, and supports graph-free geometric analysis on high-dimensional images where nearest neighbors break down.

Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, YuCheng, Bo Zheng 等

Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior reasoning potential. Indeed, for specific constraint satisfaction tasks (e.g., sudoku puzzles), this capability has proven to be highly advantageous. However, in this paper, we reveal that for general reasoning tasks (e.g., mathematics and coding), arbitrary order generation may in fact limit the reasoning potential of dLLMs. We find that dLLMs tend to exploit this order flexibility to bypass high-uncertainty tokens that are crucial for exploration, leading to a premature collapse of solution coverage. This observation motivates a rethink of RL approaches for dLLMs, where considerable complexities, such as handling combinatorial trajectories and intractable likelihoods, are often devoted to preserving this flexibility. We demonstrate that effective reasoning can be better elicited by simply forgoing arbitrary order and applying standard Group Relative Policy Optimization (GRPO) instead. Our approach, **JustGRPO**, is minimalist yet surprisingly effective (e.g., 89.1% accuracy on GSM8K) while fully retaining the parallel decoding ability of dLLMs.

General Machine Learning · Transfer, Multitask and Meta-learning

Qi Ma, Chen-Yang Wang, Dehong Gao, Deng-Ping Fan

Prompt learning for vision-language models (VLMs) primarily follows end-to-end or decoupled routes to balance base and new task performance, but suffers a fundamental bottleneck: sample-wise optimization within task-specific feature spaces traps models in local optima, hindering global optimality. To address this, we identify a key insight that VLMs can be prompted within a Coupled Prompt Field-a shared space where base and new tasks are mutually constrained-and present AlignedNorm, which enforces the field coupling. By dynamically aligning the norms of prompts to VLMs' native scale, our method enables joint optimization of both tasks. Without complex designs, our method matches leading decoupled approaches on 15 datasets across 4 experimental settings, offering both a new perspective and a practical solution to the local-optima dilemma in prompt learning.

Ishaan Singh Chandok, Core Francisco Park

Scientific data annotation, such as tracking animals in video or proofreading neural reconstructions, remains bottlenecked by the “last mile” problem: even with strong automation, verification and correction consume substantial human effort. Standard approaches train models to directly predict annotations, discarding the rich supervision in how experts navigate, click, verify, and correct. We introduce a framework for studying behavioral cloning on scientific annotation: 9 synthetic tasks paired with synthetic annotations that simulate realistic human strategies including exploration, mistake correction, and strategic decision-making. Our experiments reveal several findings. First, skills emerge hierarchically: models learn GUI mechanics before task-critical decisions, and commit fewer mistakes than the training data while retaining the ability to correct errors when they occur. Second, scaling models on multi-task behavioral cloning shows that larger models are more data efficient, but exhibit worse decision-making despite similar placement accuracy. Third, multi-task pretraining enables efficient fine-tuning to new tasks, while training from scratch fails entirely. Fourth, linear probes reveal that models internally represent latent variables of the annotation process such as task phase and data position; interestingly, we find a shared mistake representation that generalizes across different annotation tasks. Overall, our framework establishes systematic benchmarks and identifies key bottlenecks, providing a foundation for scaling behavioral cloning to real-world scientific data annotation.

Deep Learning · Large Language Models

Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, YuCheng, Bo Zheng 等

Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior reasoning potential. Indeed, for specific constraint satisfaction tasks (e.g., sudoku puzzles), this capability has proven to be highly advantageous. However, in this paper, we reveal that for general reasoning tasks (e.g., mathematics and coding), arbitrary order generation may in fact limit the reasoning potential of dLLMs. We find that dLLMs tend to exploit this order flexibility to bypass high-uncertainty tokens that are crucial for exploration, leading to a premature collapse of solution coverage. This observation motivates a rethink of RL approaches for dLLMs, where considerable complexities, such as handling combinatorial trajectories and intractable likelihoods, are often devoted to preserving this flexibility. We demonstrate that effective reasoning can be better elicited by simply forgoing arbitrary order and applying standard Group Relative Policy Optimization (GRPO) instead. Our approach, **JustGRPO**, is minimalist yet surprisingly effective (e.g., 89.1% accuracy on GSM8K) while fully retaining the parallel decoding ability of dLLMs.

General Machine Learning · Everything Else

CHEN WANG, Yongli Hu, Huajie Jiang, Kan Guo, Tengfei Liu, Junbin Gao, Yanfeng Sun, Baocai Yin

We reconceptualize Personalized Multimodal Federated Learning (PMFL) by treating missing modalities as intrinsic structural identities that constrain each client to a distinct Riemannian submanifold, rather than deficiencies to be compensated. To resolve the tension between identity preservation and cross-client collaboration, we cast PMFL as an identity-aware potential game and seek a geometry-consistent equilibrium instead of a single full-modality global optimum. We propose GeoEvo, which realizes this equilibrium via Fisher--Riemannian evolutionary dynamics: Natural Evolution Strategies for curvature-adaptive local exploration and subspace-constrained particle swarm updates for symbiotic knowledge transfer. GeoEvo admits a Lyapunov potential and, with a monotone acceptance rule, guarantees potential dissipation; in non-convex regimes it achieves an $O(1/\sqrt{T})$ stationarity rate, implying convergence to first-order Nash equilibria, and empirically improves personalization and robustness across diverse modality-missing identities.

Applications · Chemistry, Physics, and Earth Sciences

Guoze Sun, Tianya Miao, Haoyang Huang, Huaguan Chen, Han Wan, Rui Zhang, Hao Sun

Geometry is central to PDE-governed systems, motivating shape optimization and inversion. Classical pipelines conduct costly forward simulation with geometry processing, requiring substantial expert effort. Neural surrogates accelerate forward analysis but do not close the loop because gradients from objectives to geometry are often unavailable. Existing differentiable methods either rely on restrictive parameterizations or unstable latent optimization driven by scalar objectives, limiting interpretability and part-wise control. To address these challenges, we propose Geometry-Aware Neural Optimizer (GANO), an end-to-end differentiable framework that unifies geometry representation, field-level prediction, and automated optimization/inversion in a single latent-space loop. GANO encodes shapes with an auto-decoder and stabilizes latent updates via a denoising mechanism, and a geometry-injected surrogate provides a reliable gradient pathway for geometry updates. Moreover, GANO supports part-wise control through null-space projection and uses remeshing-free projection to accelerate geometry processing. We further prove that denoising induces an implicit Jacobian regularization that reduces decoder sensitivity, yielding controlled deformations. Experiments on three benchmarks spanning 2D Helmholtz, 2D airfoil, and 3D vehicles show state-of-the-art accuracy and stable, controllable updates, achieving up to $+55.9\%$ lift-to-drag improvement for airfoils and $\sim 7\%$ drag reduction for vehicles.

Deep Learning · Large Language Models

Karanpartap Singh, Neil Band, Ehsan Adeli

As the cost of pretraining large language models grows, there is continued interest in strategies to improve learning efficiency during this core training stage. Motivated by cognitive development, where humans gradually build knowledge as their brains mature, we propose Curriculum-Guided Layer Scaling (CGLS), a framework for compute-efficient pretraining that synchronizes increasing data difficulty with model growth through progressive layer stacking (i.e. gradually adding layers during training). At the 100M parameter scale, using a curriculum transitioning from synthetic short stories to general web data, CGLS outperforms baseline methods on the question-answering benchmarks PIQA and ARC. Pretraining at the 1.2B scale, we stratify the DataComp-LM corpus with a DistilBERT-based classifier and progress from general text to highly technical or specialized content. Our results show that progressively increasing model depth alongside sample difficulty leads to better generalization and zero-shot performance on various downstream benchmarks. Altogether, our findings demonstrate that CGLS unlocks the potential of progressive stacking, offering a simple yet effective strategy for improving generalization on knowledge-intensive and reasoning tasks.

Chufan Shi, Cheng Yang, Yaokang Wu, Linghao Jin, Bo Shui, Taylor Berg-Kirkpatrick, Xuezhe Ma

Vision-Language Models (VLMs) frequently generate self-reflective statements during reasoning, such as ``let me check the figure again.'' Do such statements trigger genuine visual re-examination, or merely represent learned textual patterns? We investigate this question through VisualSwap, an image-swap probing framework: after a model generates reasoning for an image, we replace it with a visually similar but semantically different image and test whether the model detects the change. We introduce VS-Bench, a benchmark of $800$ image pairs curated from MathVista, MathVerse, MathVision, and MMMU-Pro. Experiments across Qwen3-VL, Kimi-VL, and ERNIE-VL families reveal a striking failure: models overwhelmingly fail to detect image changes, with accuracy dropping by up to 60\%. Counterintuitively, thinking models exhibit nearly 3$\times$ greater vulnerability than their instructed counterparts, and scaling provides no mitigation. However, multi-turn interaction with user instructions can restore visual grounding, while self-generated reflective statements during continuous generation cannot. Attention analysis reveals the underlying mechanism: self-reflection does not increase attention to visual tokens, whereas user instructions substantially elevate it. Our findings reveal that current VLMs tend to say rather than actually see when claiming visual re-examination.

Probabilistic Methods · Monte Carlo and Sampling Methods

Xiaoyu Wang, Jonathan Huggins

Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD-Gibbs) provides a highly scalable approach to approximate Bayesian inference in latent variable models. However, it remains unclear how to tune the algorithm's hyperparameters in a principled manner to ensure the uncertainty estimates are statistically meaningful. In this work, we address this gap in tuning guidance by developing a statistical scaling limit theory for SGLD-Gibbs. We derive a joint asymptotic limit for the global parameters and latent variables under appropriate space-time rescaling. We show that global parameters converge to a diffusion-type limit, while individual latent variables converge to a jump process reflecting their intermittent Gibbs updates. This joint jump-diffusion structure reveals how latent-variable randomness contributes to the stationary distribution of the global parameters. We leverage our results to provide explicit guidance on hyperparameter tuning for SGLD-Gibbs that ensures meaningful uncertainty quantification. Our empirical results show that SGLD-Gibbs with our tuning guidance leads to better parameter estimates and uncertainty quantification than stochastic variational inference.

Theory · Game Theory

Kenshi Abe, Mitsuki Sakamoto, Kaito Ariu, Atsushi Iwasaki

This paper proposes an asymmetric perturbation technique for solving bilinear saddle-point optimization problems, commonly arising in minimax problems, game theory, and constrained optimization. Perturbing payoffs or values is known to be effective in stabilizing learning dynamics and equilibrium computation. However, it requires decreasing perturbation magnitudes to ensure convergence to an equilibrium in the underlying game, resulting in a slower rate. To overcome this, we introduce an asymmetric perturbation approach, where only one player's payoff function is perturbed. Exploiting the near-linear structure of bilinear problems, we show that, for a sufficiently small perturbation, the equilibrium strategy of the asymmetrically perturbed game coincides with an equilibrium strategy of the original game. Building on this property, we develop a perturbation-based learning algorithm with a linear last-iterate convergence rate to an equilibrium strategy of the original game, and we further show how to construct a parameter-free procedure that retains a linear rate. Finally, we empirically demonstrate fast convergence toward equilibria in both normal-form and extensive-form games.

Reinhard Heckel, Mahdi Soltanolkotabi, Christos Thrampoulidis

Reinforcement learning with verifiable rewards has driven recent advances in LLM post-training, in particular for reasoning. Policy optimization algorithms generate a number of responses for a given prompt and then effectively weight the corresponding gradients depending on the rewards. The most popular algorithms including GRPO, DAPO, and RLOO focus on ambiguous prompts, i.e., prompts with intermediate success probability, while downgrading gradients with very easy and very hard prompts. In this paper, we consider asymmetric prompt weightings that assign higher weights to prompts with low success probability. We find that asymmetric weighting particularly benefits from-scratch RL (as in R1-Zero), where training traverses a wide accuracy range, and less so post-SFT RL where the model already starts at high accuracy. We also provide theory that characterizes prompt weights which minimize the time needed to raise success probability from an initial level to a target accuracy under a fixed update budget. In low-success regimes, where informative responses are rare and response cost dominates, these optimal weights become asymmetric, upweighting low success probabilities and thereby accelerating effective-time convergence.

Qingdong He, Chaoyi Wang, Peng TANG, Yifan Yang, Xiaobin Hu

Video subtitle removal is essential for content localization and media re-editing, yet existing mask-guided diffusion methods face critical limitations: training inefficiency requiring extensive annotations and full model fine-tuning, inference complexity demanding explicit mask sequences, and static prior utilization unable to adapt to quality variations. We present CLEAR (Context-aware Learning for End-to-end Adaptive subtitle Removal), a lightweight adapter-based framework addressing these challenges through three technical innovations. First, self-supervised prior learning (Stage I) extracts occlusion guidance from video pairs using pixel differences as weak supervision, eliminating annotation dependency while learning generalizable subtitle features across languages. Second, LoRA-based adaptive refinement (Stage II) enables parameter-efficient training that preserves pre-trained visual priors while achieving true mask-free end-to-end inference without external detection modules. Third, adaptive focal weighting dynamically adjusts prior influence based on local quality assessment, effectively handling diverse subtitle styles and noisy guidance signals. Extensive experiments demonstrate CLEAR's superior performance in multilingual subtitle removal while requiring only 0.77% trainable parameters, establishing a new paradigm for efficient video text removal without inference-time mask dependencies.

Applications · Health / Medicine

Ziyang Liu, Ruiqiang Xiao, Chang Huang, KIEREN YU, Siyuan He, Kaishun WU

Continuous ECG monitoring is clinically valuable, but scaling it beyond electrodes to comfortable long-term use motivates contactless mmWave sensing. In practice, mmWave-to-ECG reconstruction is severely constrained by the scarcity of high-quality synchronized recordings and poor cross-subject generalization. To overcome these bottlenecks, we propose \textbf{Cardio-mmFlow}, a Gaussian-prior-free physics-informed flow matching framework that synthesizes realistic mmWave radar signals from abundant clinical ECG corpora. It learns a direct transport trajectory between the latent manifolds of ECG and radar. To capture subject-dependent propagation differences, we incorporate a simplified mass--spring--damper inspired physical prior and inject it into the flow dynamics via feature-wise linear modulation for personalization. Extensive experiments show that our system have generate high fidelity radar data in both signal and latent domains. It significantly improve zero-shot downstream mmWave$\rightarrow$ECG task, and enable Atrial Fibrillation classification with synthetic data. Further analysis evaluate the model interpretability.

Theory · Domain Adaptation and Transfer Learning

Chenghan Xie, Jose Blanchet, Renyuan Xu

Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise naturally in transfer learning, where the score difference provides the mechanism for adapting a pre-trained model to a new target distribution, and in diffusion model-based post-training methods such as discriminator guidance. Existing estimators for score differences in these settings either lack of statistical consistency or are difficult to scale up in high-dimensions. We propose a statistically consistent and scalable estimator for score differences based on Sobolev regularization, which plays a crucial role in ensuring consistency and stablizing the training in the small-sample regime. Mathematically, we establish a convergence rate of $\tilde{\mathcal{O}}(n^{-\frac{s-1}{d+2s-2}})$ where $d$ is the dimension and $s$ denotes the smoothness of the underlying densities, and provide a minimax lower bound of $\tilde{\Omega}(n^{-\frac{2(s-1)}{d+2s}})$ (in mean-squared error). Empirically, our estimator exhibits significantly improved stability in small-sample regimes compared to existing methods. We demonstrate its effectiveness on real-world tasks, including transfer learning for ECG signal generation, where it substantially outperforms non-regularized score difference estimators in downstream classification performance.