论文检索

General Machine Learning · Hardware and Software

Zongze Li, Jingyu Liu, Zach Xu, Yineng Zhang, Tahseen Rabbani, Ce Zhang

Prefill-Decode (PD) disaggregation has become the standard architecture for modern LLM inference engines, which alleviates the interference of two distinctive workloads. With the growing demand for multi-turn interactions in chatbots and agentic systems, we re-examined PD in this case and found two fundamental inefficiencies: (1) every turn requires prefilling the new prompt and response from the last turn, and (2) repeated KV transfers between prefill and decode nodes saturate the bandwidth, leading to high latency and even service degradation. Our key insight is that not all prefill operations are equally disruptive: append-prefill---processing only the new input tokens while reusing cached KV states---incurs substantially less decoding slowdown than full prefill. This motivates routing append-prefill to decode nodes locally. However, through comprehensive analysis, we show that no single fixed routing strategy satisfies all Service Level Objectives (SLOs) simultaneously. Based on this insight, we propose Prefill Prefill-capable Decode (PPD) disaggregation, a dynamic routing system that decides when to process Turn 2+ requests locally on decode nodes using cached KV states. PPD adapts to varying SLOs via configurable weights and seamlessly integrates with traditional PD deployments. With extensive evaluations, we show that PPD reduces Turn 2+ time-to-first-token (TTFT) by 68% while maintaining competitive time-per-output-token (TPOT), effectively alleviating KV transfer congestion under high load. We believe PPD represents a flexible and efficient paradigm for multi-turn LLM serving.

Applications · Computer Vision

Fuyun Wang, Yuanzhi Wang, Xu Guo, Sujia Huang, Tong Zhang, Dan Wang, Xin Liu, Hui Yan, Zhen Cui

Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to reconcile fidelity and diversity, often hampered by distribution misalignment and overfitting, respectively. To mitigate this, we introduce Anomaly Preference Optimization (APO), a novel paradigm that reformulates anomaly generation as a preference learning problem. Central to our approach is an implicit preference alignment mechanism that leverages real anomalies as positive references, deriving optimization signals directly from denoising trajectory deviations without requiring costly human annotation. Furthermore, we propose a Time-Aware Capacity Allocation module that dynamically distributes model capacity along the diffusion timeline— prioritizing structural diversity during highnoise phases while enhancing fine-grained fidelity in low-noise stages. During inference, a hierarchical sampling strategy modulates the coherencealignment trade-off, enabling precise control over generation. Extensive experiments demonstrate that significantly outperforms existing baselines, achieving state-of-the-art performance in both realism and diversity.

Deep Learning · Large Language Models

Yuanyang Li, Xue Yang, Longyue Wang, Weihua Luo, Hongyang Chen

Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental noise. We introduce $\textbf{ComplexMCP}$, a benchmark designed to evaluate agents in these rigorous conditions. Built on the Model Context Protocol (MCP), $\textbf{ComplexMCP}$ provides over 300 meticulously tested tools derived from 7 stateful sandboxes, ranging from office suites to financial systems. Unlike existing datasets, our benchmark utilizes a seed-driven architecture to simulate dynamic environment states and unpredictable API failures, ensuring a deterministic yet diverse evaluation. We evaluate various LLMs across full-context and RAG paradigms, revealing a stark performance gap: even top-tier models fail to exceed a 60% success rate, far trailing human performance 90%. Granular trajectory analysis identifies three fundamental bottlenecks: (1) $\textbf{tool retrieval saturation}$ as action spaces scale; (2) $\textbf{over-confidence}$, where agents skip essential environment verifications; and (3) $\textbf{strategic defeatism}$, a tendency to rationalize failure rather than pursuing recovery. These findings underscore the insufficiency of current agents for interdependent workflows, positioning $\textbf{ComplexMCP}$ as a critical testbed for the next generation of resilient autonomous systems.

General Machine Learning · Hardware and Software

Duc Hoang, Aarush Gupta, Philip Harris

Ultrafast online learning is essential for high-frequency systems, such as controls for quantum computing and nuclear fusion, where adaptation must occur on sub-microsecond timescales. Meeting these requirements demands low-latency, fixed-precision computation under strict memory constraints, a regime in which conventional Multi-Layer Perceptrons (MLPs) are both inefficient and numerically unstable. We identify key properties of Kolmogorov-Arnold Networks (KANs) that align with these constraints. Specifically, we show that: (i) KAN updates exploiting B-spline locality are sparse, enabling superior on-chip resource scaling, and (ii) KANs are inherently robust to fixed-point quantization. By implementing fixed-point online training on Field-Programmable Gate Arrays (FPGAs), a representative platform for on-chip computation, we demonstrate that KAN-based online learners are significantly more efficient and expressive than MLPs across a range of low-latency and resource-constrained tasks. To our knowledge, this work is the first to demonstrate model-free online learning at sub-microsecond latencies.

General Machine Learning · Representation Learning

Yanjie Qiu, Xiaodong Yue, Xuhui Fan, Yufei Chen, Jie Shi, Wei Liu

Concept Embedding Models (CEMs) advance interpretable AI by extending Concept Bottleneck Models (CBMs) through semantic concept embeddings, providing an important solution in high-stakes domains such as medical diagnosis where accuracy and interpretability are critical. However, a fundamental limitation persists: existing CEMs inherently assume concept independence, critically overlooking the highly complex dependencies among concepts. To address this, we propose an Evidential Copula Concept Embedding Model (EC-CEM) that redefines the joint distribution over concepts, capturing inter-concept dependencies while maintaining a flexible structure that decouples the marginal concept distributions from their dependency structure. In particular, EC-CEM relaxes the concept independence assumption and uniquely integrates Copula theory with evidential deep learning to define a joint distribution over concepts. The proposed EC-CEM also develops two training objectives that aim at classification and concept modeling simultaneously. We provide theoretical justification via variational inference and demonstrate empirical superiority through extensive experiments.

Deep Learning · Large Language Models

Zeping Min, Weihang Xu, Zhengzhong You, Wotao Yin, Xinshang Wang

Natural language to optimization (NL2Opt) requires translating unstructured text into executable mathematical models. Beyond simple syntax errors, this task suffers from silent modeling failures, where incorrect formulations execute successfully but yield invalid results. We propose Draft-and-Audit RL (DA-RL), a framework that learns optimization modeling as a two-step iterative workflow. Unlike inference-time scaffolds that rely on intermediate solver feedback to guide repairs, DA-RL optimizes a shared-parameter policy using terminal-only verification: the model is rewarded solely based on the execution of the final audited program. This constraint forces the model to internalize rubric-guided revision as a learned capability and encourages the emergence of cross-turn synergy, where the policy learns to generate drafts that are structurally amenable to self-correction.

Deep Learning · Large Language Models

Qiang Zhang, Boli Chen, Fanrui Zhang, Ruixue Ding, Shihang Wang, Qiuchen Wang, Yinfeng Huang, Haonan Zhang, Rongxiang Zhu, Xin Li 等

Reinforcement learning (RL) has advanced LLM agents on verifiable tasks but remains challenging for open-ended tasks with vast solution spaces (e.g., complex travel planning). Lacking objective ground truth, current RL algorithms rely on reward models assigning scalar scores to individual responses. We contend such pointwise scoring induces discrimination collapse: reward model fails to distinguish subtle advantages among trajectories, compressing intra-group rewards into a narrow range. This drowns effective reward signals in reward model noise, causing optimization stagnation. To address this, we propose ArenaRL, a reinforcement learning paradigm shifting from pointwise scalar scoring to intra-group relative ranking. ArenaRL introduces a process-aware pairwise evaluation with multi-level rubrics for fine-grained relative scoring. Meanwhile, we construct an intra-group adversarial arena and devise a tournament-based ranking scheme to obtain stable advantage signals. ArenaRL achieves high-precision advantage estimation with only $O(N)$ computational complexity, striking a favourable balance between efficiency and accuracy. Furthermore, to address the lack of full-cycle benchmarks for open-ended agents, we introduce two high-quality benchmarks: Open-Travel and Open-DeepResearch, encompassing full training and multi-dimensional evaluation pipelines. Extensive experiments across three open-ended tasks validate the effectiveness of ArenaRL.

Applications · Language, Speech and Dialog

Karthik Somayaji NS, Yuxuan Yin, Peng Li

In critical domains like clinical reporting, legal analysis, and policy drafting, large language models (LLMs) are increasingly expected to produce extended, fact‑rich narratives rather than isolated sentences. Reliable uncertainty quantification in such long‑form outputs is crucial. Existing techniques either assign a single confidence score to an entire paragraph or evaluate factual consistency by comparing extracted atomic facts across multiple generations. Some recent approaches represent fact–paragraph relationships using bipartite entailment graphs and derive uncertainty from fact centrality. However, these methods ignore the explicit dependencies among facts within a paragraph and the structural and semantic variation across multiple LLM outputs for the same prompt, missing a key source of uncertainty specific to long‑form generation. We propose **GAUSS** (**G**raph‑**A**ssisted **U**ncertainty **Q**uantification using **S**tructure and **S**emantics), a principled framework that models each generated paragraph as a semantic graph of atomic facts and their relations. We posit that uncertainty arises from structural and semantic discrepancies among these graphs across different samples. **GAUSS** quantifies uncertainty as the expected alignment cost between the semantic graph of an anchor paragraph and those of alternative generations. By capturing both semantic content and structural coherence, **GAUSS** offers a more interpretable and theoretically grounded measure of uncertainty than coarse, sentence‑level scores.

General Machine Learning · Kernel methods

Rustem Takhanov, Zhenisbek Assylbekov

Conditionally positive definite (CPD) kernels are defined with respect to a function class $\mathcal{F}$. It is well known that such a kernel $K$ is associated with its native space (defined analogously to an RKHS), which in turn gives rise to a learning method --- called conditional kernel ridge regression (conditional KRR) due to its analogy with KRR --- where the estimated regression function is penalized by the square of its native space norm. This method is of interest because it can be viewed as classical linear regression, with features specified by $\mathcal{F}$, followed by the application of standard KRR to the residual (unexplained) component of the target variable. Methods of this type have recently attracted increasing attention. We study the statistical properties of this method by reducing its behavior to that of KRR with another fixed kernel, called the residual kernel. Our main theoretical result shows that such a reduction is indeed possible, at the cost of an additional term in the expected test risk, bounded by $\mathcal{O}(1/\sqrt{N})$, where $N$ is the sample size and the hidden constant depends on the class $\mathcal{F}$ and the input distribution. This reduction enables us to analyze conditional KRR in the case where $K$ is positive definite and $\mathcal{F}$ is given by the first $k$ principal eigenfunctions in the Mercer decomposition of $K$. We also consider the setting where $\mathcal{F}$ consists of $k$ random features from a random feature representation of $K$. It turns out that these two settings are closely related. Both our theoretical analysis and experiments confirm that conditional KRR outperforms standard KRR in these cases whenever the $\mathcal{F}$-component of the regression function is more pronounced than the residual part.

Reinforcement Learning · Deep RL

Huy Le, Onur Celik, Denis Blessing, Tai Hoang, Claas Voelcker, Axel Brunnbauer, Felix Richter, Michael Volpp, Gerhard Neumann

Reinforcement learning with massively parallel simulations has become an emerging trend; however, most existing approaches still rely on simple Gaussian policy parameterizations. Diffusion models provide a more expressive policy class and have shown strong performance on challenging control problems, yet most diffusion-based RL methods are designed for offline or off-policy training. In this work, we ask whether diffusion policies can be trained effectively in the massively parallel, on-policy regime. To this end, we introduce Trust-region Diffusion Policies (TruDi), which enables diffusion policies for on-policy RL with massively parallel simulations. This setting is particularly challenging because the data distribution changes quickly across updates, making stable training with complex policies difficult. TruDi addresses this by integrating a trust-region optimization rule to enforce a KL-divergence constraint over the entire diffusion trajectory, rather than only at the final denoising step. Empirically, we evaluate TruDi on a diverse set of 4 massively parallel RL benchmarks comprising a total of 73 tasks. Across these tasks, TruDi consistently outperforms or is on-par with strong baselines on standard tasks and achieves clear gains on more challenging humanoid control tasks, establishing a strong new baseline for massively parallel on-policy RL.

Deep Learning · Large Language Models

Zhe Zheng, Wenqi Zhang, Xiaohe Zhou, Guiyang Hou, Xinyu Mei, Tianyang Mao, Anni PIAO, Shengpei Jiang, Yongliang Shen, Yueting Zhuang 等

Multimodal large language models (MLLMs) have demonstrated remarkable reasoning capabilities over internalized knowledge. However, current research overlooks contextual reasoning, the ability to reason based on the relevant information present in the context. To investigate this issue, we construct the Visual Contextual Reasoning Benchmark (ContextReasonV-Bench), and our analysis reveals two predominant failure modes: \textit{context neglect}, where models rely on pre-trained knowledge instead of contextual information, and \textit{superficial pattern matching}, where models exploit shallow correlations rather than genuine patterns. To address these limitations, we propose a two-stage approach that progressively establishes and reinforces contextual pattern acquisition. The first stage establishes an "analyze-then-solve" reasoning paradigm through supervised fine-tuning (SFT). We then employ a context-aware reinforcement learning (RL) framework that integrates context-aware reward modeling with hierarchical advantage estimation to encourage the model to identify genuine contextual patterns. This approach yields Context-Aware Reasoner (CAR), a model that achieves 38.14\% accuracy on ContextReasonV-Bench, improving the base model by 22.09\%. Notably, CAR exhibits strong generalization to tasks not seen during training, confirming that our approach enhances genuine contextual reasoning capability.

Deep Learning · Large Language Models

Boya Xiong, Shuo Wang, Weifeng Ge, Guanhua CHEN, Yun Chen

Supervised Fine-Tuning (SFT) empowers Large Language Models (LLMs) with exceptional performance on specialized tasks, but it yields dense, high-dimensional delta parameters that pose severe storage and distribution challenges. Singular Value Decomposition (SVD)-based compression offers a compact representation for such delta parameters, but existing methods adopt heuristic quantization without clarifying underlying mechanisms, leading to poor generalizability. In this work, we propose PrinMix, a rigorous SVD-based framework that models quantization as an optimization problem, grounding the design in mathematical mechanisms. We first theoretically derive quantization error and identify a key singular-value-dominated scaling mechanism, which mathematically proves the necessity of mix-precision quantization. We then model the quantization scheme as a 0/1 Integer Linear Programming (ILP) problem, which yields optimal bit-budget-constrained solutions without empirical assumptions. Furthermore, PrinMix integrates a Reconstruction Target Correction (RTC) method to compensate for errors from the $\mathbf{V}$-then-$\mathbf{U}$ sequential quantization process. Extensive experiments confirm PrinMix performs well: for 7B LLMs, PrinMix outperforms SOTA Delta-CoMe on challenging benchmarks by 22.3\% on AIME2024 and 6.1\% on GQA.

General Machine Learning · Kernel methods

Zonghao Chen, Aratrika Mustafi, Pierre Glaser, Anna Korba, Arthur Gretton, Bharath K. Sriperumbudur

We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either lack tractable numerical implementation ($f$-divergence flows) or require strong assumptions and modifications, such as noise injection, to ensure convergence (Maximum Mean Discrepancy flows). In contrast, DrMMD flow can simultaneously (i) guarantee near-global convergence for a broad class of targets in both continuous and discrete time, and (ii) be implemented in closed form using only samples. The former is achieved by leveraging the connection between the DrMMD and the $\chi^2$-divergence, while the latter comes by treating DrMMD as MMD with a de-regularized kernel. Our numerical scheme employs an adaptive de-regularization schedule throughout the flow to optimally balance the trade-off between discretization errors and deviations from the $\chi^2$ regime. The potential application of the DrMMD flow is demonstrated across several numerical experiments, including a large-scale setting of training student/teacher networks.

Deep Learning · Large Language Models

Hyunji (Alex) Nam, Haoran Li, Natasha Jaques

While post-training has successfully improved large language models across a variety of domains from open-ended text generation to mathematics, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited and new high-quality data is expensive to collect. More fundamentally, true intelligence goes far beyond tasks that are easily verified. Therefore, there is a need for self-improvement frameworks that allow models to improve without external oversight. We propose **Mutual Information-based Preference Optimization (MIPO)**, a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioned on the correct prompt and a negative response conditioned on a random or incomplete prompt; then train with Direct Policy Optimization. We show that this connects to maximizing pointwise mutual information between prompts and model responses under the base policy. Empirical results with the Llama- (1, 3B) and Qwen- (1.5, 3, 7B) Instruct models show that MIPO achieves 4-38\% improvements on personalization tasks from real-user datasets (PRISM, Community Alignment). Surprisingly, MIPO can be more generally applied to a suite of benchmark tasks (e.g., math and multiple-choice answering), yielding 3\% and 18\% improvements for smaller 1B models, *without any additional data or labels.*

Deep Learning · Graph Neural Networks

Wei Huang, Hanchen Wang, Dong Wen, Wenjie Zhang, Ying Zhang, Xuemin Lin

Graph Edit Distance (GED), which aims to find an edit path with minimum number of edit operations to transform one graph into another, is a fundamental NP-hard problem and a widely used graph similarity measure. Recent matching-based hybrid approaches have demonstrated better scalability than A* search-based hybrids by reformulating GED as a graph matching problem. In these methods, a neural network predicts a single deterministic node matching matrix, from which top-$k$ node mappings are extracted iteratively to derive candidate edit paths. However, these methods often suffer from highly correlated candidates that easily lead to suboptimal solutions, while the iterative extraction becomes inefficient for large $k$. In this paper, we propose DiffGED, the first generative approach for GED computation. Specifically, we formulate the graph matching problem as a generative task, and employ a diffusion-based model to generate multiple diverse node matching matrices simultaneously, from which diverse node mappings can be efficiently extracted. The generative diversity introduced by the diffusion process enables DiffGED to avoid suboptimal solutions and achieve superior solution quality close to the exact solution. Experiments on real-world datasets show that DiffGED generates multiple diverse edit paths with accuracy comparable to exact solutions, while running faster than existing hybrid approaches.

Applications · Computer Vision

Yunhong Lu, Qichao Wang, Hengyuan Cao, Xiaoyin Xu, Min Zhang

Existing preference datasets for text-to-image (T2I) models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose generation is naturally indexed by a specific prior noise sample and follows a nearly straight denoising trajectory. In contrast, prior DPO-style alignment for diffusion models commonly estimates trajectories using an independent forward noising process, which can be mismatched to the true reverse dynamics and introduces unnecessary variance. We propose Prior Noise-Aware Preference Optimization (PNAPO), an off-policy alignment framework specialized for rectified flow. PNAPO augments preference data by retaining the paired prior noises used to generate each winner/loser image, turning the standard (prompt, winner, loser) triplet into a sextuple. Leveraging the straight-line property of RF, we estimate intermediate states via noise–image interpolation, which constrains the trajectory estimation space and yields a tighter surrogate objective for preference optimization. In addition, we introduce a dynamic regularization strategy that adapts the DPO temperature/regularization based on (i) the reward gap between winner and loser and (ii) training progress, improving stability and sample efficiency. Experiments on state-of-the-art RF T2I backbones (FLUX.1-dev and SD3-Medium) show that PNAPO consistently improves preference metrics while substantially reducing training compute compared to Diffusion-DPO.

Optimization · Discrete and Combinatorial Optimization

Debraj Banerjee, Santanu Mahapatra, Kunal Narayan Chaudhury

The generalized Ising problem captures a broad spectrum of hard combinatorial problems, including MAX-CUT, Number Partitioning (NPP), and Maximum Independent Set. In this work, we consider the notion of one-flip local minima for this problem. We construct a polynomial relaxation and prove that there exists a one-to-one correspondence between the local minima of the relaxation and the one-flip minima of the original Ising problem. This guarantee reduces the Ising problem to finding the local minima of a smooth function, allowing us to leverage scalable gradient-based optimizers such as ADAM. We demonstrate that our method achieves strong performance across challenging benchmarks, including spin-glass models, MAX-CUT, and NPP.

Social Aspects · Security

Ali Ebrahimpour-Boroojeny, Yian Wang, Hari Sundaram

In this paper, we reveal a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause information leakage about the forgotten class. We further propose a simple unlearning strategy to mitigate this issue. We introduce Class Membership Inference Attack (CMIA) that uses the probabilities the model assigns to neighboring classes to detect unlearned samples. We find that existing unlearning methods are vulnerable to CMIA across multiple datasets. We then propose a new fine-tuning objective that mitigates this privacy leakage by approximating, for forget-class inputs, the distribution over the remaining classes that a retrained-from-scratch model would produce. To construct this approximation, we estimate inter-class similarity and tilt the target model’s distribution accordingly. The resulting Tilted REWeighting (TREW) distribution serves as the desired distribution during fine-tuning. We also show that across multiple benchmarks, TREW matches or surpasses existing unlearning methods on prior unlearning metrics. More specifically, on CIFAR-10, it reduces the gap with retrained models by $19\%$ and $46\%$ for U-LiRA and CMIA scores, accordingly, compared to the SOTA method for each category.

Applications · Computer Vision

Rongjin Guo, Guan Huankang, Rynson Lau

Salient Object Ranking (SOR) aims to study how humans visually explore complex scenes by predicting an ordered sequence of objects that attracts our attention. Existing SOR approaches typically model this ranking deterministically, assuming a single, fixed ranking sequence of attention. However, such deterministic SOR fails to capture the true nature of human attention. We observe that human attention shifts exhibit variability and stochasticity, showing that the next object of fixation is not a definitive choice but rather a probability distribution. Yet, existing SOR methods and evaluation metrics do not account for this inherent randomness. To address this fundamental problem, we propose ProbSOR, a novel Probabilistic Salient Object Ranking model that explicitly learns the uncertainty of attention shifts by incorporating Group Relative Policy Optimization (GRPO). We leverage a Vision-Language Model (VLM) as the foundation for ProbSOR to identify salient objects and infer their ranked order, utilizing a segmentation decoder for precise object extraction. We also propose a new metric tailored to ProbSOR, as existing SOR metrics only support deterministic rankings. Further, we construct a ProbSOR dataset comprising 15,000 probabilistic SOR samples, to support both model training and evaluation. Extensive experiments demonstrate that ProbSOR achieves strong performances in salient object ranking under both our proposed and traditional benchmarks.

Optimization · Non-Convex

John Hood, Aaron Schein

Despite the ubiquity of multiway data across scientific domains, there are few user-friendly tools that fit tailored nonnegative tensor factorizations. Researchers may use gradient-based automatic differentiation (which often struggles in nonnegative settings), choose between a limited set of methods with mature implementations, or implement their own model from scratch. As an alternative, we introduce NNEinFact, an einsum-based multiplicative update algorithm that fits any nonnegative tensor factorization expressible as a tensor contraction by minimizing one of many user-specified loss functions (including the $(\alpha,\beta)$-divergence). To use NNEinFact, the researcher simply specifies their model with a string. NNEinFact converges to a local minimum of the loss, supports missing data, and fits to tensors with hundreds of millions of entries in seconds. Empirically, NNEinFact fits custom models which outperform standard ones in heldout prediction tasks on real-world tensor data by over 37% and attains less than half the test loss of gradient-based methods while converging up to 90 times faster.