论文检索

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.

General Machine Learning · Transfer, Multitask and Meta-learning

Siyang Guo, Junbo Wang, Zibin Zheng

As pre-trained models evolve rapidly, transferring fine-tuning knowledge to updated models without retraining has become a critical challenge. Most existing methods reuse parameter updates, yet the same dataset can induce substantially different updates across base models due to mismatched local loss landscapes, making such transfer unstable. We instead adopt a Bayesian-updating perspective: a base model defines a prior, while fine-tuning contributes a task-update factor that is prior-agnostic, thereby making it feasible to reuse the update across base models. Specifically, we formalize a reusable task-update factor by requiring *invariance across base models* and *a fixed-dimensional parameterization*. Our main theoretical result shows that such reusable factors exist when the variational family is a half-space, and it is already maximal among convex families. In particular, an ideal regime arises when the priors and their Bayesian posteriors remain within a shared exponential family, as it always admits a reusable update factor. Building on this existence, we propose ***B**ayesian Task Update **Transfer*** (*BTransfer*), which extracts a reusable task-update factor from a single fine-tuning run and applies it to a new prior. For deep networks, we implement *BTransfer* with a ``lift–transfer–return'' pipeline: 1) lift model parameters to distributions; 2) transfer the extracted task-update factor in the exponential family distributions; and 3) return the updated posterior distribution to parameter space. Extensive experiments demonstrate that our approach effectively reuses fine-tuning knowledge across models without post-training.

Social Aspects · Accountability, Transparency, and Interpretability

Xinyan Jiang, Ninghao Liu, Di Wang, Lijie Hu

Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress (displacement) and Stability (curvature), we reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns (stalled displacement with high curvature fluctuations). Leveraging these signatures, our probabilistic framework achieves competitive performance and superior robustness across diverse benchmarks. Crucially, TRACED bridges geometry and cognition by mapping high curvature to "Hesitation Loops'' and displacement to ''Certainty Accumulation'', offering a physical lens to decode the internal dynamics of machine thought.

Theory · Reinforcement Learning and Planning

Chenjie Mao, Yi Fan, Ning Zhang, Chongjie Zhang

This paper studies \emph{preference-based reinforcement learning} (PbRL), where agents learn from comparative, trajectory-level feedback rather than numeric rewards. While PbRL has seen rapid empirical and theoretical progress, existing analyses are largely confined to restricted settings and fail to jointly capture the outcome-based and comparison-based nature of preference feedback. We prove that under a broad \emph{general function approximation} framework, PbRL admits a $\sqrt{T}$ regret guarantee. In particular, we introduce a simple and provably efficient algorithm, \emph{Recursive Trajectory-based Preference Q-Learning} (RTPQ), and establish its regret bound while explicitly accounting for the trajectory-level and comparative structure of preferences. Our analysis is characterized by a new complexity measure, the \emph{Dual Episodic Eluder Dimension} (DEED), which quantifies the intrinsic difficulty of PbRL. We show that for linear MDPs, the DEED scales as $\mathcal{O}(dH)$, yielding a regret bound of $\tilde{\mathcal{O}}(dH\sqrt{T}\max(H^{3/2},\,1/\kappa))$, where $\kappa$ is a problem-dependent constant. This bound is near-optimal up to horizon- and problem-dependent factors when compared to standard reward-based linear MDPs. In addition, our framework recovers the best-known regret bounds in the special cases of dueling bandits and standard outcome-based reinforcement learning. Overall, our results provide a general regret guarantee for PbRL with outcome-based preference feedback and broad function approximation.

Kecheng Chen, Ziru Liu, Xijia Tao, Hui Liu, Xinyu Fu, Suiyun Zhang, Dandan Tu, Lingpeng Kong, Rui Liu, Haoliang Li

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics—such as confidence or entropy—which inherently lack a more reliable perspective, leading to sub-optimal generation quality. To address this, we propose **C**oherent **C**ontextual **D**ecoding (**CCD**), a novel inference framework built upon two core innovations. First, CCD bypasses the potential bias of the single context to leverage historical contexts for approximating the marginal distribution of token prediction, leading to better sequence coherence and the early rejection of sub-optimal paths. More importantly, we demonstrate that this mechanism is theoretically equivalent to modeling the consistency of historical steps via the conditional mutual information between contexts and token predictions. Finally, CCD achieves significantly milder performance degradation under highly parallel decoding scenarios compared to baselines. Empirically, our method achieves a simultaneous enhancement in both inference speed and performance across diverse benchmarks on Dream and LLaDA.

Social Aspects · Fairness

Robin Staab, Jasper Dekoninck, Maximilian Baader, Martin Vechev

Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide. Despite their widespread adoption, growing reliance on their outputs raises significant concerns, particularly as users may be exposed to model-inherent biases that disadvantage or stereotype certain groups. However, existing bias benchmarks commonly rely on simple templated prompts or restrictive multiple-choice questions that fail to capture the complexity of real-world user interactions. In this work, we address this gap by introducing a counterfactual framework that automatically generates realistic, open-ended questions for LLM bias evaluation. Through iterative question mutation, our approach further systematically explores areas where models are most susceptible to exhibit biased behavior. Beyond just detecting harmful biases, we also capture increasingly relevant response dimensions, such as asymmetric refusals and explicit bias acknowledgment. Building on this, we construct CAB, a diverse and human-verified benchmark for realistic and nuanced bias evaluations on current frontier LLMs. Our evaluation using CAB highlights the continued need for fairness research by demonstrating that all examined models exhibit persistent biases across certain scenarios.

Social Aspects · Accountability, Transparency, and Interpretability

Guanxu Chen, Dongrui Liu, Tao Luo, Lijie Hu, Qihao Lin, Jing Shao

Large language models (LLMs) are becoming increasingly capable, but the mechanisms of their thinking and decision-making processes remain unclear. Chain-of-thoughts (CoTs) have been commonly utilized to externalize LLMs' thinking, but this strategy fails to accurately reflect LLMs' thinking process. Techniques based on LLMs' hidden representations provide an inner perspective to improve the monitorability of their latent thinking. However, previous methods only try to develop external modules instead of making LLMs themselves easier to monitor. In this paper, we propose a novel method, TELLME, improving the transparency of LLMs and helping monitors identify unsuitable and sensitive behaviors. Furthermore, we showcase the effectiveness of TELLME on detoxification tasks, where LLMs achieve consistent improvement among multimodal test sets, distinct architectures, and varying parameter scales. We further analyze TELLME's improvement on LLMs' generalization ability from both optimal transport theory and empirical perspectives.

General Machine Learning · Transfer, Multitask and Meta-learning

Qun Yang, Enneng Yang, Li Shen, Wei Chen, Long Lan

Continual learning with large pre-trained models offers significant potential for cross-task knowledge accumulation, but faces critical challenges such as catastrophic forgetting and parameter interference, especially when historical data is unavailable. Existing approaches typically rely on sequential fine-tuning or model merging strategies, yet often overlook the impact of loss landscape sharpness and dominant singular value directions, which leads to subspace misalignment and severe knowledge forgetting. In this paper, we propose the Sharpness-Aware Isotropic Merging (SAIM) framework, which introduces targeted optimizations in both the fine-tuning and merging stages to address these issues. Specifically, SAIM consists of two synergistic modules: (1) a Sharpness-Aware Block Coordinate Descent (SA-BCD) optimizer that guides the model toward flatter minima and selectively updates the most task-sensitive parameters, thereby mitigating parameter interference and enhancing robustness; (2) an adaptive isotropic merging algorithm that dynamically balances the singular value spectrum across tasks, effectively preventing the model from overemphasizing any single task direction, maintaining balanced knowledge representation, and improving subspace alignment. Extensive experiments on vision and language benchmarks demonstrate that SAIM achieves 5-10% higher accuracy than existing methods and maintains robust performance as the number of tasks increases. Ablation studies further validate the effectiveness of the SA-BCD fine-tuning strategy in promoting flat minima and reducing parameter interference, as well as its compatibility with various merging approaches.