论文检索

General Machine Learning · Representation Learning

Xuan Yang, Jiayu Liu, Yuhang Lai, Hao Xu, Zhenya Huang, Ning Miao

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as a powerful tool for interpretability, existing approaches predominantly operate at the token level, creating a granularity mismatch when capturing more critical step-level information, such as reasoning direction and semantic transitions. In this work, we propose step-level sparse autoencoder~(\name), which serves as an analytical tool to disentangle different aspects of LLMs' reasoning steps into sparse features. Specifically, by precisely controlling the sparsity of a step feature conditioned on its context, we form an information bottleneck in step reconstruction, which splits incremental information from background information and disentangles it into several sparsely activated dimensions. Experiments on multiple base models and reasoning tasks show the effectiveness of the extracted features. By linear probing, we can easily predict surface-level information, such as generation length and first token distribution, as well as more complicated properties, such as the correctness and logicality of the step.These observations indicate that LLMs should already at least partly know about these properties during generation, which provides the foundation for the self-verification ability of LLMs.

Applications · Health / Medicine

Jeonghyeon Kim, Nathaniel Blalock, Ameya Kulkarni, Kensuke Nakamura, Philip Romero

Antibodies originate from germline immunoglobulin gene templates and are diversified by somatic hypermutation during affinity maturation. This process produces sequences in which conserved germline residues provide structural scaffolding, complemented by rare non-germline substitutions that refine antigen binding and functional properties. Despite this important biological organization, current antibody language models (ALMs) treat all residues equivalently, blurring the distinction between germline-encoded conservation and adaptive non-germline variation. When applied to germline-dominated repertoires—reflecting shared germline starting points from which diversity arises—this induces a germline bias in which rare but functionally important non-germline (NGL) mutations are systematically down-weighted as statistical noise. Here, we introduce PRISM, a germline-aware antibody language model that explicitly represents germline and non-germline residues as distinct token types. This biologically informed representation achieves state-of-the-art pseudo-perplexity in hypervariable complementarity-determining regions (CDRs) and enables controllable sequence generation for precise paratope engineering while preserving germline-mediated framework stability. PRISM further exhibits improved zero-shot prediction of binding affinity relative to existing ALMs. Together, these results demonstrate that incorporating biologically grounded sequence representations substantially improves antibody language modeling.

General Machine Learning · Representation Learning

Jiwoo Kim, Swarajh Mehta, Hao-Lun Hsu, Hyunwoo Ryu, Yudong Liu, Miroslav Pajic

Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-matrix dimensions. Generation is further complicated by permutation symmetries that allow networks to model similar input-output functions while having widely different, unaligned parameterizations. In this work, we introduce Neural Network Diffusion Transformers (NNiTs), which generate weights in a width-agnostic manner by tokenizing weight matrices into patches and modeling them as locally structured fields. We establish that Graph HyperNetworks (GHNs) with a convolutional neural network (CNN) decoder structurally align the weight space, creating the local correlation necessary for patch-based processing. Focusing on MLPs, where permutation symmetry is especially apparent, NNiT generates fully functional networks across a range of architectures. Our approach jointly models discrete architecture tokens and continuous weight patches within a single sequence model. On ManiSkill3 robotics tasks, NNiT achieves $>85\%$ success on architecture topologies unseen during training, while baseline approaches fail to generalize.

Optimization · Discrete and Combinatorial Optimization

Yang Huang, Yifan Zhang, Jian Cheng

We propose an OT-guided sampling framework for solving graph combinatorial optimization through exact multilinear relaxation. Graph combinatorial optimization problems can be written as quadratic unconstrained binary optimization(QUBO). Leveraging a classical result in combinatorial optimization, we obtain a continuous multi-linear relaxation of QUBO that is exact, in the sense that it preserves the optimal binary solutions. The challenge is that the resulting energy landscape is highly nonconvex. We address this by treating the objective as an energy function and optimizing via sampling from the induced Boltzmann distribution to escape poor local optima. Viewing sampling as transporting a simple reference distribution to the target distribution, we use optimal transport to characterize more efficient probability flow and derive a stochastic optimal control problem whose solution yields an optimal sampling dynamics. We parameterize the control policy with graph neural networks to approximate the optimal control. Experiments show improved solution quality and efficiency over strong combinatorial and learning-based baselines.

General Machine Learning · Scalable Algorithms

Miklós Máté Badó, Kristian Fenech

Influence functions are a standard tool for data debugging and unlearning, but they become impractical for **high-query** subset workloads such as large-$K$ cross-validation, repeated resampling, or interactive what-if analysis as each subset query typically requires an expensive inverse-curvature solve. We introduce **Clustered Influence Functions (CiF)**, which turns subset influence into an **amortized subset oracle**. We build a compact cache once by clustering training gradients, solve a damped Generalised Gauss-Newton system only for cluster means, and answer new subset queries by a linear recombination using cluster membership counts. This yields per-query cost of $O(Cp)$ linear in the cache size $C$, and the number of model parameters $p$. We further provide a diagnostic error bound that decomposes approximation error into a **clustering scatter** term and a **solver residual** term, making the accuracy-compute tradeoff explicit through the cache budget and solver tolerance. Evaluations across MNIST, CIFAR-10, show that CiF matches per-query influence rankings while significantly reducing the total runtime in high-$Q$ regimes, enabling influence-based workflows that are otherwise computationally prohibitive.

Applications · Chemistry, Physics, and Earth Sciences

jieyuan pei, Zhuoxuan Li, Wei Li, Haobo Zhang, jiawei jiang, Jianwei Zheng

Neural operators have emerged as powerful surrogates for solving PDEs, significantly accelerating scientific computation. While transformer-based architectures offer unmatched flexibility for irregular domains, they suffer from a fundamental efficiency gap: standard attention mechanisms assign uniform interaction budgets to all token pairs, neglecting the physical reality that far-field interactions are often compressible. To address this mismatch, we draw inspiration from classical fast solvers that exploit hierarchical near-far decompositions. We further observe that embedding such tree-structured hierarchies in Euclidean space incurs inherent distortion, whereas hyperbolic space naturally accommodates exponential branching. Consequently, we propose \textbf{Hyperbolic Neural Operator (HNO)}, which leverages intrinsic hyperbolic geometry to instantiate a continuous Gibbs kernel based on stabilized geodesic distances on the Lorentz hyperboloid. This design imposes a geometric inductive bias that naturally enjoys robust multi-scale routing akin to the Fast Multipole Method (FMM), yet within a unified, learnable attention mechanism. Empirically, HNO achieves state-of-the-art accuracy on six PDE benchmarks and two large-scale unstructured CFD tasks, reducing the mean relative $\ell_2$ error by up to 40\% compared to leading baselines. Codes are attached and will be available online.

Optimization · Convex

Junchi Yan, Liangliang Shi, Jiaxi Liu, Fangyuan Zhou, Wenzheng Pan, Zhongteng Gui, Yihui Tu

One essential limitation of neural networks is how to enforce (hard) constraints on prediction. We propose a plug-in, differentiable layer, which involves a fast implicit (convex) optimization procedure to enforce the general linear constraint. It aims to minimize a divergence between unconstrained and constrained outputs. Connecting to and beyond existing handcrafted layers, we show that our layer degrades to classic layers like Softmax, Sinkhorn and tanh etc. when the corresponding constraint is enforced by KL-divergence minimization. We further show that by replacing the KL-div with a Euclidean distance, a closed-form solution can be derived for highly-efficient constraint enforcing. We evaluate the above two variants of layers, termed as BLCLayer and GLCLayer, with their corresponding neural solver BLCNet and GLCNet with simple MLP/GNN-like backbone. Experiments on linear programming, as well as two real-world problems: partial graph matching and portfolio allocation which involve other discrete constraints.

Applications · Computer Vision

Weihao Bo, Jingwen Qin, Yanpeng Sun, Fei Shen, Xiaofan Li, Zechao Li

Real-world agricultural counting often operates in the extreme regime of \textbf{Dense and Indiscernible Object Counting (DIOC)}, where targets are tiny, clustered, and highly camouflaged. To facilitate research in this domain, we introduce \textbf{DIOCblueberry}, a large-scale benchmark that pushes the boundaries of visual perception. Unlike general datasets with salient objects, DIOCblueberry features extreme occlusion and camouflage. Compared to the popular FSC147 benchmark, it contains \textbf{1.9$\times$ more instances} per image (avg. 108) with an average box pixel ratio that is \textbf{7.9$\times$ smaller}, serving as a rigorous testbed for model robustness. Standard counting methods struggle in these scenarios due to severe visual ambiguity and scale mismatch. To address this, we propose \textbf{MaskCount}, a coarse-to-fine framework that incorporates semantic guidance. MaskCount leverages Vision-Language Models (CLIP) to generate pseudo segmentation masks for background suppression and employs a contrastive loss to maximize feature discriminability between fruits and foliage. Additionally, we design an edge-aware cropping mechanism to resolve boundary truncation in dense clusters. Extensive experiments demonstrate that MaskCount achieves a new state-of-the-art, reducing MAE and RMSE by \textbf{49.16\%} and \textbf{70.50\%} respectively on DIOCblueberry, with strong generalization to other agricultural scenes.

Deep Learning · Foundation Models

renjie lu, Xulong Zhang, Xiaoyang Qu, Jianzong Wang, Shangfei Wang

Unified Multimodal models (UMMs) built on a single architecture have shown impressive performance in both understanding and generation. We identify a fundamental challenge lies in inductive biases induced by distinct supervision signals: generation branch prefers high-fidelity, fine-grained representations capable of reconstruction, while the understanding favours semantically discriminative embeddings that remain invariant to task-irrelevant factors. Consequently, optimizing these complementary but non-equivalent objectives within a monolithic backbone leads to mutual impairment instead of enhancement. In this paper, we first analyze the root cause of this interference in unified backbones and reveal a complementary structure in their internal representations. Motivated by the observation, we propose DIVA, a self-improved post-training framework that transforms the representation divergence into interior synergy. By explicitly factorizing the visual representation into shared and unique components based on two complementary information flow, DIVA enables both the understanding and generation branches to achieve beneficial transferring while preserving the integrity of unique information from cross-flow interference via mutual information estimation. Despite its generality, our method consistently achieves improvements across visual understanding (+7.82%) and generation (+8.46%). The official code is available at: https://anonymous.4open.science/r/DIVA-D225.

Reinforcement Learning · Everything Else

Hai Zhong, Xun Wang, Zhuoran Li, Longbo Huang

By leveraging differentiable dynamics, Reparameterization Policy Gradient (RPG) achieves high sample efficiency. However, current approaches are hindered by two critical limitations: the under-utilization of computationally expensive dynamics Jacobians and inherent training instability. While sample reuse offers a remedy for under-utilization, no prior principled framework exists, and naive attempts risks exacerbating instability. To address these challenges, we propose Reparameterization Proximal Policy Optimization (RPO). We first establish that under sample reuse, RPG naturally optimizes a PPO-style surrogate objective via Backpropagation Through Time, providing a unified framework for both on- and off-policy updates. To further ensure stability, RPO integrates a clipped policy gradient mechanism tailored for RPG and employs explicit Kullback-Leibler divergence regularization. Experimental results demonstrate that RPO maintains superior sample efficiency and consistently outperforms or achieves state-of-the-art performance across diverse tasks.

Deep Learning · Large Language Models

Zicheng Xu, Xiuyi Lou, Guanchu Wang, Yu-Neng Chuang, Feng Luo, Guangyao Zheng, Alex Szalay, Zirui Liu, Vladimir Braverman

Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to uncover high-quality solutions. To address these limitations, we propose **D**ecoding **T**ree **S**ketching (DTS), a plug-and-play decoding framework for structural multi-trajectory exploration and reasoning selection. For reasoning exploration, DTS sketches a backbone tree of the reasoning space by selectively branching at decision tokens. For reasoning selection, guided by length-accuracy anti-correlation, DTS designs an early termination to prioritize short and reliable trajectories during decoding. Experimental results across four LRMs and datasets demonstrate that DTS significantly enhances accuracy by **14\%** and reduces repetitive generation by **8\%** on average. Notably, DTS enables smaller models to outperform larger models with 10$\times$ the size, highlighting its potential to strengthen reasoning capabilities.

Social Aspects · Accountability, Transparency, and Interpretability

Manjiang Yu, Hongji Li, Junwei Chen, Xue Li, Priyanka Singh, YANG CAO, Lijie Hu

Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weights. Existing methods typically apply a fixed intervention uniformly across all inputs. However, we find that the appropriate intervention direction and strength vary substantially across samples, and such indiscriminate intervention leads to degradation of general capabilities on benign inputs. To address these challenges, we propose Multi-Adapter Representation Interventions via Energy Calibration (MARI). Specifically, we introduce a competitive multi-adapter mechanism in which specialized experts capture non-linear correction patterns and adaptively determine the appropriate intervention direction and strength for different samples. Furthermore, we design an energy-based gating module that leverages internal propagation dynamics to distinguish inputs that are applicable for intervention. Extensive experiments across diverse model families and parameter scales demonstrate that MARI achieves state-of-the-art alignment performance. Our method significantly improves performance on TruthfulQA, BBQ, and safety benchmarks, while maintaining and even improving general capabilities on tasks such as MMLU and ARC. Our code will be released upon acceptance.

Optimization · Convex

Jannis Halbey, Daniel Deza, Max Zimmer, Christophe Roux, Bartolomeo Stellato, Sebastian Pokutta

We present a constructive lower bound of $\Omega(1/\sqrt{\varepsilon})$ for Frank-Wolfe (FW) when both the objective and the constraint set are smooth and strongly convex, showing that the known uniform $\mathcal{O}(1/\sqrt{\varepsilon})$ guarantees in this regime are tight. It is known that under additional assumptions on the position of the optimizer, FW can converge linearly. However, it remained unclear whether strong convexity of the set can yield rates \emph{uniformly} faster than $\mathcal{O}(1/\sqrt{\varepsilon})$, i.e., irrespective of the position of the optimizer. To investigate this question, we focus on a simple yet representative problem class: minimizing a strongly convex quadratic over the Euclidean unit ball, with the optimizer on the boundary. We analyze the dynamics of FW for this problem in detail and develop a novel computational approach to construct worst-case FW trajectories, which is of independent interest. Guided by these constructions, we develop an analytical proof establishing the lower bound.

Social Aspects · Accountability, Transparency, and Interpretability

Zhuoran Zhang, Tengyue Wang, Xilin Gong, Yang Shi, Haotian Wang, Di Wang, Lijie Hu

Multimodal Large Language Models (MLLMs) must resolve conflicts when modalities provide contradictory information, a process we term "modality following". We propose a framework that deconstructs this behavior into case-specific relative reasoning uncertainty and a model's stable inherent preference. By evaluating diverse MLLMs, we establish a universal law: the probability of following a modality decreases monotonically as its relative reasoning uncertainty increases, which is robustly preserved across diverse uncertainty indices. This law allows us to quantify a "balance point" where uncertainties are subjectiveized, offering a principled measure of modality bias that is disentangled from unimodal capabilities. Probing the internal decision-making reveals that this conflict resolution is a high-level cognitive process: in ambiguous regions near the balance point, models exhibit significant "concept oscillations," where top predictions vacillate between modalities specifically within the middle-to-late layers. Finally, we demonstrate the framework's utility for preference steering through Supervised Fine-Tuning (SFT). We find that data efficiency is governed by reasoning uncertainty: training on easy samples (where one modality dominates) fails to generalize, whereas targeting the identified ``boundary cases" is essential for robust preference alignment and suppressing internal vacillation.

Applications · Health / Medicine

Mingqing Wang, Zhiwei Nie, ATHANASIOS VASILAKOS, Yonghong He, Zhixiang Ren

Proteins encode diverse functions within complex three-dimensional structures, yet most deep learning representations remain highly entangled, obscuring the biophysical signals that underlie function. Here we introduce ProtDiS, a knowledge-guided framework that decomposes pretrained protein micro-environment embeddings into biologically grounded and task-relevant dimensions. Inspired by the information bottleneck principle, ProtDiS learns representations that balance informativeness and compression, yielding structural features that are more specific, independent, and information-efficient, and achieving consistent improvements across twelve downstream tasks, with the largest gains under structure-based splits. Protein- and residue-level analyses further show that ProtDiS differentiates proteins with similar folds but divergent functions and captures fine-grained biophysical signals critical. These findings suggest that knowledge–guided decomposition provides a general and interpretable approach for structuring latent spaces in protein structural modeling.

General Machine Learning · Unsupervised and Semi-supervised Learning

Raymond Li, Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to construct semantically-grounded soft label targets using Language Models (LMs) by projecting the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary to obtain contextually enriched supervision signals. By training the topic models to reconstruct the soft labels using the LM hidden states, our method produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Experiments on three datasets show that our method achieves substantial improvements in topic coherence, purity over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications.\footnote{we will release the code upon publishing the paper.}

Social Aspects · Accountability, Transparency, and Interpretability

Wenshuo Dong, Jiaming Zhang, Shaopeng Fu, Hongbin Lin, Di Wang, Lijie Hu

As predictive models are increasingly deployed in high-stakes settings such as credit approval, there is a growing need for post-hoc methods that provide recourse to affected individuals. Many such models operate on tabular data, where features correspond to real-world attributes. Recently, in-context learning (ICL) has enabled large language models to perform tabular prediction by conditioning on labeled examples at inference time, without explicit training. However, algorithmic recourse for tabular decision-making under ICL remains largely unexplored. In this work, we present the first study of algorithmic recourse for tabular data under ICL. We carry out a theoretical analysis, showing that recourse remains well-defined and bounded, and we characterize how recourse converges toward classical solutions as the context size increases. In practice, we propose a novel zeroth-order recourse framework, Adaptive Subspace Recourse for In-Context Learning (ASR-ICL), that efficiently generates actionable and sparse recourse for black-box ICL models. The proposed framework naturally extends to multi-class tabular tasks. Experiments across multiple real-world datasets and models demonstrate that ASR-ICL achieves recourse quality comparable to existing methods with fewer queries and empirically confirm the predicted convergence behavior, supporting our theoretical analysis.

General Machine Learning · Data

Zhongzhi Li, Xuansheng Wu, Yijiang Li, Lijie Hu, Ninghao Liu

The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches to constructing post-training data quantify diversity using text-based metrics that capture linguistic variation, but such metrics provide only weak signals for the task-relevant features that determine downstream performance. In this work, we introduce ***Feature Activation Coverage* (FAC)** which measures data diversity in an interpretable feature space. Building upon this metric, we further propose a diversity-driven data synthesis framework, named **FAC Synthesis**, that first uses a sparse autoencoder to identify missing features from a seed dataset, and then generates synthetic samples that explicitly reflect these features. Experiments show that our approach consistently improves both data diversity and downstream performance on various tasks, including instruction following, toxicity detection, reward modeling, and behavior steering. Interestingly, we identify a shared, interpretable feature space across model families (i.e., LLaMA, Mistral, and Qwen), enabling cross-model knowledge transfer. Our work provides a solid and practical methodology for exploring data-centric optimization of LLMs.

General Machine Learning · Data

Zhongzhi Li, Xuansheng Wu, Yijiang Li, Lijie Hu, Ninghao Liu

The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches to constructing post-training data quantify diversity using text-based metrics that capture linguistic variation, but such metrics provide only weak signals for the task-relevant features that determine downstream performance. In this work, we introduce ***Feature Activation Coverage* (FAC)** which measures data diversity in an interpretable feature space. Building upon this metric, we further propose a diversity-driven data synthesis framework, named **FAC Synthesis**, that first uses a sparse autoencoder to identify missing features from a seed dataset, and then generates synthetic samples that explicitly reflect these features. Experiments show that our approach consistently improves both data diversity and downstream performance on various tasks, including instruction following, toxicity detection, reward modeling, and behavior steering. Interestingly, we identify a shared, interpretable feature space across model families (i.e., LLaMA, Mistral, and Qwen), enabling cross-model knowledge transfer. Our work provides a solid and practical methodology for exploring data-centric optimization of LLMs.

Qinan Yu, Alexa Tartaglini, Peter Hase, Carlos Guestrin, Christopher Potts

Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR represent how a model gets to its answer. In this paper, we develop two metrics for critically examining this assumption: Causal Importance of Reasoning (CIR), which measures the cumulative effect of reasoning tokens on the final answer (faithfulness), and Sufficiency of Reasoning (SR), which measures whether a verifier can arrive at an unambiguous answer based on the reasoning alone (verifiability). Through experiments with the Qwen2.5 model series and ReasoningGym tasks, we find that: (1) While RLVR does improve task accuracy, it does not reliably improve CIR or SR, calling the role of reasoning in model performance into question. (2) A small amount of SFT before RLVR can be a remedy for low CIR and SR. (3) CIR and SR can be improved even without SFT by applying auxiliary CIR/SR rewards on top of the outcome-based reward. This joint reward matches the accuracy of RLVR while also leading to causally important and sufficient reasoning. These results show that RLVR does not always lead models to rely on reasoning in the way that is commonly thought, but this issue can be remedied with simple modifications to the post-training procedure.