论文检索

Applications · Computer Vision

Wen Zhang, Qin Ren, Wenjing Liu, Haibin Ling, Chenyu You

Accurate nuclear instance segmentation is a pivotal task in computational pathology, supporting data-driven clinical insights and facilitating downstream translational applications. While large vision foundation models have shown promise for zero-shot biomedical segmentation, most existing approaches still depend on dense supervision and computationally expensive fine-tuning. Consequently, training-free methods present a compelling research direction, yet remain largely unexplored. In this work, we introduce SPROUT, a fully training- and annotation-free prompting framework for nuclear instance segmentation. SPROUT leverages histology-informed priors to construct slide-specific reference prototypes that mitigate domain gaps. These prototypes progressively guide feature alignment through a partial optimal transport scheme. The resulting foreground and background features are transformed into positive and negative point prompts, enabling the Segment Anything Model (SAM) to produce precise nuclear delineations without any parameter updates. Extensive experiments across multiple histopathology benchmarks demonstrate that SPROUT achieves competitive performance without supervision or retraining, establishing a novel paradigm for scalable, training-free nuclear instance segmentation in pathology.

Deep Learning · Large Language Models

Qi Cao, Shuhao Zhang, Ruizhe Zhou, Ruiyi Zhang, Peijia Qin, Pengtao Xie

Model routing chooses which language model to use for each query. By sending easy queries to cheaper models and hard queries to stronger ones, it can significantly reduce inference cost while maintaining high accuracy. However, most existing routers treat this as a fixed choice among a small set of models, which makes them hard to adapt to new models or changing budget constraints. In this paper, we propose SCOPE (Scalable and Controllable Outcome Performance Estimator), a routing framework that goes beyond model selection by predicting their cost and performance. Trained with reinforcement learning, SCOPE makes reasoning-based predictions by retrieving how models behave on similar problems, rather than relying on fixed model names, enabling it to work with new, unseen models. Moreover, by explicitly predicting how accurate and how expensive a model will be, it turns routing into a dynamic decision problem, allowing users to easily control the trade-off between accuracy and cost. Experiments show that SCOPE is more than just a cost-saving tool. It flexibly adapts to user needs: it can boost accuracy by up to **25.7\%** when performance is the priority, or cut costs by up to **95.1\%** when efficiency matters most.

Applications · Computer Vision

Mingyu Kang, Yuna Jeong, Junhyeong Park, Hyein Seo, Yong Suk Choi

Large Vision–Language Models (LVLMs) have shown outstanding performance across various multimodal tasks, but they still suffer from hallucinations, where they generate incorrect information by relying on language priors without visual grounding. To alleviate this issue, prior work has explored contrastive decoding approaches that compare the output of an original LVLM with that of a contrast branch. However, existing methods typically generate contrast logits through preprocessing of the input image. Such input-level perturbations fail to sufficiently reflect the model’s internal degree of visual reliance during the decoding process. To address this limitation, we propose Dynamic Entropy-Guided Attention Perturbation (DEGAP) for contrastive decoding in LVLMs. DEGAP performs contrastive decoding by directly perturbing visual attention and leveraging the resulting logits, without requiring any additional image preprocessing. To this end, we analyze the layer-wise effects of visual attention perturbations and, based on these observations, dynamically select the layers at which attention perturbation is applied according to the model’s confidence. Experimental results on seven benchmarks demonstrate that DEGAP effectively mitigates various types of hallucinations and consistently outperforms state-of-the-art methods in general VQA performance.

Applications · Computer Vision

Zanwu Liu, Chao Yuan, Bo Li, Xiaowei Zhang, Guanglin Niu

Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to substantial resolution gaps between low-resolution (LR) queries and high-resolution (HR) gallery images. Prior approaches commonly rely on super-resolution (SR) or resolution-invariant representation learning, which often increases system complexity and may not directly address the feature mismatch induced by resolution degradation. In this work, we report a new empirical finding: after averaging out identity-specific variation, the HR--LR feature discrepancy produced by standard ReID backbones exhibits a consistent, resolution-related semantic direction in the embedding space. We further support this observation with statistical analyses based on Canonical Correlation Analysis (CCA) and Pearson correlation analysis. Motivated by this finding, we propose Vector Panning Feature Alignment (VPFA), a lightweight post-hoc module that learns to pan LR features along the learned resolution direction to obtain pseudo-HR representations. VPFA operates after feature extraction and can be integrated into existing ReID systems with negligible overhead. Extensive experiments on multiple CR-ReID benchmarks show that VPFA achieves state-of-the-art performance while improving efficiency compared to SR-based or jointly trained alternatives.

Theory · Probabilistic Methods

Guangyi Zhang, Yunlong Cai, Guanding Yu, Osvaldo Simeone

We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a semi-supervised risk-monitoring approach based on prediction-powered inference (PPI). PPRM constructs anytime-valid lower bounds on the running risk by combining synthetic labels with a small set of true labels. Harmful shifts are detected via a threshold-based comparison with an upper bound on the nominal risk, satisfying assumption-free finite-sample guarantees in the probability of false alarm. We demonstrate the effectiveness of PPRM through extensive experiments on image classification, large language model (LLM), and telecommunications monitoring tasks.

Applications · Computer Vision

Ziyi Wang, Peiming Li, Xinshun Wang, Yang Tang, Kai-Kuang Ma, Mengyuan Liu

Multimodal large language models (MLLMs) exhibit strong visual-language reasoning, yet remain confined to their native modalities and cannot directly process structured, non-visual data such as human skeletons. Existing methods either compress skeleton dynamics into lossy feature vectors for text alignment, or quantize motion into discrete tokens that generalize poorly across heterogeneous skeleton formats. We present SkeletonLLM, which achieves universal skeleton understanding by translating arbitrary skeleton sequences into the MLLM's native visual modality. At its core is DrAction, a differentiable, format-agnostic renderer that converts skeletal kinematics into compact image sequences. Because the pipeline is end-to-end differentiable, MLLM gradients can directly guide the rendering to produce task-informative visual tokens. To further enhance reasoning capabilities, we introduce a cooperative training strategy: Causal Reasoning Distillation transfers structured, step-by-step reasoning from a teacher model, while Discriminative Finetuning sharpens decision boundaries between confusable actions. SkeletonLLM demonstrates strong generalization on diverse tasks including recognition, captioning, reasoning, and cross-format transfer---suggesting a viable path for applying MLLMs to non-native modalities. Code is available in the Supplementary Material.

Applications · Computer Vision

Zunxu Liu, Aiqiu Wu, Zhaofan Qiu, Yingwei Pan, Ting Yao, Tao Mei

We present DMSampler, a framework that accelerates diffusion reinforcement learning by using fast distillation models as its training-time sampling engine. It overcomes the key bottleneck of sampling from the policy model—typically requiring around 50 denoising steps—by employing a co-evolving distilled sampler that needs only 4–8 steps, yielding an order-of-magnitude speedup. This approach inherently offers several advantages: it drastically reduces sampling steps, operates without classifier-free guidance to prevent potential optimization bias, and often yields superior sample quality due to more deterministic denoising trajectories. The core of DMSampler is a dual iterative training scheme, where the policy model and the distillation sampler are alternately optimized to convergence. This scheme is enhanced by two key innovations: hybrid distillation sampling, which blends outputs from both models to ensure training stability, and reward-aware distillation, which explicitly preserves high-reward capabilities during knowledge transfer. Extensive experiments on text-to-image and text-to-video generation demonstrate that DMSampler produces a final policy model which achieves state-of-the-art performance—significantly boosting textual accuracy on OCR-specific benchmarks and outperforming existing diffusion RL methods on comprehensive GenEval and VBench benchmarks.

Deep Learning · Large Language Models

Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia (Shirley) Wu, Junxiong Wang, Alpay Ariyak, Qingyang Wu, Samir Khaki 等

Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, for example by independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical bottleneck is _verification_: sampling is only effective if correct solutions can be reliably identified among candidates. While existing approaches typically evaluate candidates independently via scalar scoring, we demonstrate that models are substantially stronger at **pairwise self-verification**. Leveraging this insight, we introduce **V1**, a framework that unifies generation and verification through efficient pairwise ranking. V1 comprises two components: **V1-Infer**, an uncertainty-guided algorithm using a tournament-based ranking that dynamically allocates self-verification compute to candidate pairs whose relative correctness is most uncertain; and **V1-PairRL**, an RL framework that **jointly trains** a single model as both generator and pairwise self-verifier, ensuring the verifier adapts to the generator's evolving distribution. On code generation (LiveCodeBench, CodeContests) and math reasoning (AIME, HMMT) benchmarks, V1-Infer improves Pass@1 by up to 10\% over pointwise verification and outperforms recent test-time scaling methods while being significantly more efficient. Furthermore, V1-PairRL achieves 7-9\% test-time scaling gains over standard RL and pointwise joint training, and improves base Pass@1 by up to 8.7\% over standard RL.

Theory · Learning Theory

Jihun Kim, Yuchen Fang, Javad Lavaei

This paper is concerned with learning the input-output mapping of general nonlinear dynamical systems. While the existing literature focuses on Gaussian inputs and benign disturbances, we significantly broaden the scope of admissible control inputs and allow correlated, nonzero-mean, adversarial disturbances. With our reformulation as a linear combination of basis functions, we prove that the $\ell_2$-norm estimator overcomes the challenges posed by an adversary with access to the full information history, provided that the attack times are sparse, *i.e.*, the probability that the system is under adversarial attack at a given time is smaller than a certain threshold. We provide an estimation error bound that decays with the input memory length and prove its optimality by constructing a problem instance that suffers from the same bound under probabilistic adversarial attacks. Our work provides a sharp input-output analysis for a generic nonlinear and partially observed system under significantly generalized assumptions compared to existing works.

Xilin Xia, Xialiang Tong, Jie Wang, Chi Ma, Shengxue Li, 白 寅岐, Yuhang Jiang, Xing Li, Jianye Hao, Mingxuan Yuan 等

Research on continual learning for LLMs seeks to acquire new skills without catastrophic forgetting of established prior knowledge. However, domain-specific fine-tuning still triggers severe, long-tailed forgetting issues even under narrow updates, particularly when the pre-training data is inaccessible. To tackle this challenge, we propose **ALER**, a data-free continual learning framework that adversarially searches for a small set of latent prompt embeddings to maximize logit divergence from a frozen reference model, proactively exposing high-risk forgetting modes at each step. It then performs online distillation from the frozen reference using the discovered embeddings to retain prior behaviors while preserving target-domain adaptation. We provide theoretical guarantees on the efficiency of our targeted repair, and extensive experiments demonstrate consistent improvements in the retention–adaptation frontier over representative baselines across $2$ domain-specific fine-tuning datasets and $6$ general-purpose benchmarks, suggesting a more proactive approach for LLM continual learning.

General Machine Learning · Data

Pengtao Xie, Li Zhang, Ruiyi Zhang

The reliance of machine learning (ML) models on large-scale, high-quality labeled training data incurs significant challenges in specialized domains where such data is expensive and difficult to obtain. A promising solution is the automatic creation of synthetic training data. However, current approaches — including data generation, automated annotation, and domain adaptation — often fail to explicitly use downstream model performance to guide the creation and refinement of synthetic training data. This position paper argues that multi-level optimization (MLO) is essential for producing high-fidelity synthetic data by enabling joint optimization of data generation, annotation, adaptation, and selection, all informed by downstream model performance. We advocate for MLO as a unified framework to address three critical challenges: (1) improving data generation by aligning synthetic data with model needs, particularly targeting class-specific deficiencies and worst-case robustness; (2) enhancing automated annotation through sequential verification and the use of large language models for more accurate labeling; and (3) enabling example-specific adaptation and selection to maximize data utility while preventing excessive over-adaptation. By facilitating end-to-end coordination across multiple learning stages, MLO offers a potential paradigm shift in synthetic data creation for data-scarce domains.

Deep Learning · Large Language Models

Shijun Li, Hilaf Hasson, Joydeep Ghosh

Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communicate with each other, have exhibited enhanced capabilities in complex tasks, such as high-quality code generation and arithmetic reasoning. However, the development of such systems often relies on handcrafted methods, and the literature on systematic design and optimization of LLM-based MAS remains limited. In this work, we introduce OMAC, a general framework designed for holistic optimization of LLM-based MAS. Specifically, we identify five key optimization dimensions for MAS, encompassing both agent functionality and collaboration structure. Building upon these dimensions, we first propose a general algorithm, utilizing two actors termed the Semantic Initializer and the Contrastive Comparator, to optimize any single dimension. Then, we present an algorithm for joint optimization across multiple dimensions. Extensive experiments demonstrate the superior performance of OMAC on diverse tasks against recent approaches. Codes are available at: https://anonymous.4open.science/r/OMAC-Sub-3FF8.

Deep Learning · Attention Mechanisms

Djohan Bonnet, Jamie Lohoff, Jan Finkbeiner, Elidona Shiqerukaj, Emre Neftci

In-Context Learning (ICL) in transformers acts as an online associative memory and is believed to underpin their high performance on complex sequence processing tasks. However, in gated linear attention models, this memory has a fixed capacity and is prone to interference, especially for long sequences. We propose Palimpsa, a self-attention model that views ICL as a continual learning problem that must address a stability-plasticity dilemma. Palimpsa uses Bayesian metaplasticity, where the plasticity of each attention state is tied to an importance state grounded by a prior distribution that captures accumulated knowledge. We demonstrate that various gated linear attention models emerge as specific architecture choices and posterior approximations, and that Mamba2 is a special case of Palimpsa where forgetting dominates. This theoretical link enables the transformation of any non-metaplastic model into a metaplastic one, significantly expanding its memory capacity. Our experiments show that Palimpsa consistently outperforms baselines on the Multi-Query Associative Recall (MQAR) benchmark and on Commonsense Reasoning tasks.

Deep Learning · Large Language Models

白 寅岐, Xialiang Tong, Jie Wang, Hongyu Liu, Longdi Pan, Jiashuo Li, Zehao Wang, Jianye Hao, Mingxuan Yuan, Feng Wu

Asynchronous reinforcement learning (RL) has shown notable success in accelerating the post-training of large language models (LLMs). However, its decoupled data generation and training paradigm introduces a fundamental distributional mismatch between data generated by stale behavior policies and current policy, leading to unstable training and degraded performance. To address this challenge, we propose D-ARL, a **D**istribution-matched **A**synchronous **R**einforcement **L**earning framework that selects high-quality asynchronous samples whose distributions are well aligned with the current policy for policy optimization. Specifically, D-ARL maintains a replay buffer that collects samples from the most recent $K$ behavior policies and proposes a variance-guided metric to select distribution-matched data. During training, D-ARL introduces a multi-behavior policy optimization algorithm to leverage the multi-source nature of the selected samples for policy update. Experiments on six widely used reasoning benchmarks show that D-ARL outperforms state-of-the-art asynchronous methods, achieving an average improvement of 6.4\% in reasoning performance and 34.7\% in sample efficiency.

Applications · Language, Speech and Dialog

Wenxuan Huang, Yu Zeng, Qiuchen Wang, Zhen Fang, Shaosheng Cao, Zheng Chu, Qingyu Yin, Shuang Chen, Zhenfei Yin, Lin Chen 等

Multimodal large language models (MLLMs) have achieved remarkable success across a broad range of vision tasks. However, constrained by the capacity of their internal world knowledge, prior work has proposed augmenting MLLMs by ``reasoning-then-tool-call'' for visual and textual search engines to obtain substantial gains on tasks requiring extensive factual information. However, these approaches typically define multimodal search in a naive setting, assuming that a single full-level or entity-level image query and few text query suffices to retrieve the key evidence needed to answer the question, which is unrealistic in real-world scenarios with substantial visual noise. Moreover, they are often limited in the reasoning depth and search breadth, making it difficult to solve complex questions that require aggregating evidence from diverse visual and textual sources. Building on this, we propose Vision-DeepResearch, which proposes one new multimodal deep-research paradigm, i.e., performs multi-turn, multi-entity and multi-scale visual and textual search to robustly hit real-world search engines under heavy noise. Our Vision-DeepResearch supports dozens of reasoning steps and hundreds of engine interactions, while internalizing deep-research capabilities into the MLLM via cold-start supervision and RL training, resulting in a strong end-to-end multimodal deep-research MLLM. It substantially outperforming existing multimodal deep-research MLLMs, and workflows built on strong closed-source foundation model such as GPT-5, Gemini-2.5-pro and Claude-4-Sonnet.

Deep Learning · Large Language Models

Yuanzhe Shen, Zisu Huang, Zhengyuan Wang, Muzhao Tian, Zhengkang Guo, Chenyang Zhang, Shuaiyu Zhou, Zengjie Hu, Dailin Li, Kaimin Wang 等

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior over long, multi-turn interactions. To bridge this gap, we introduce \textbf{TRIP-Bench}, a long-horizon benchmark grounded in realistic travel-planning scenarios. TRIP-Bench leverages real-world data, offers 18 curated tools and 40+ travel requirements, and supports automated evaluation. It includes splits of varying difficulty; the hard split emphasizes long and ambiguous interactions, style shifts, feasibility changes, and iterative version revision. Dialogues span up to 15 user turns, can involve 150+ tool calls, and may exceed 200k tokens of context. Experiments show that even advanced models achieve at most 50\% success on the easy split, with performance dropping below 10\% on hard subsets. We further propose GTPO, an online multi-turn reinforcement learning method with specialized reward normalization and reward differencing. Applied to Qwen2.5-32B-Instruct, GTPO improves constraint satisfaction and interaction robustness, outperforming Gemini-3-Pro in our evaluation. We expect TRIP-Bench to advance practical long-horizon interactive agents, and GTPO to provide an effective online RL recipe for robust long-horizon training.

General Machine Learning · Transfer, Multitask and Meta-learning

Joonho Kim, Seyoung Park

We propose a transfer learning framework for estimating high-dimensional Ising models that characterize interactions between discrete binary variables from limited target samples and multiple auxiliary datasets of unknown relevance. Our algorithm, termed Trans-Ising, builds upon a two-stage procedure that first obtains an initial estimator via nodewise $\ell_1$-regularized logistic regression on the target data together with selected auxiliary samples, and then refines it using a target-only correction step with a folded-concave penalty to improve edge selection accuracy. To decide which auxiliary sources to transfer from and reduce the risk of negative transfer, we introduce a loss-based screening rule based on out-of-sample pseudolikelihood evaluation on held-out target data. We also establish asymptotic error bounds and selection consistency for the proposed estimator under standard high-dimensional conditions. Extensive simulations and real data applications show that Trans-Ising consistently outperforms competing methods.

Shuqing Luo, Yilin Guan, Pingzhi Li, Hanrui Wang, Tianlong Chen

Test-time scaling (TTS) can boost LLM reasoning through long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware sparse decoding methods can achieve state-of-the-art performance under constrained FLOP budget, but are mainly constrained by both sequential-dependent page filtering and coarse-grained token selection, hampering the serving efficiency and model performance on TTS tasks under high concurrency and long CoT scenarios, where token selection can even occupy higher runtime than the forward pipeline itself. In this paper, we first find that the query state of the current decoding token can be approximated in a unified manner from a short sliding window of recent queries, enabling training-free query-aware sparsity without sequential dependency in the decoding loop. Based on the findings, we propose $\texttt{\textbf{AsyncSpade}}$, an asynchronous framework for efficient TTS, built on two core components: $\textbf{(1) a novel light-weight temporal-regressive module}$ that predicts the next-token query state, and $\textbf{(2) an asynchronous disaggregated framework}$ that decouples the KV cache selection from the auto-regressive decoding loop, overlapping the token-level KV selection with the forward inference computation through asynchronism, thereby eliminating the sequential dependency without sacrificing model performance. We validate the effectiveness of $\texttt{AsyncSpade}$ on common LLM serving setups with an A100 node, where $\texttt{AsyncSpade}$ can fully overlap KV-cache operations with the inference pipeline within a certain workload range, $\textbf{achieving theoretical optimal time-per-output-token~(TPOT)}$. Specifically, $\texttt{AsyncSpade}$ delivers over 20% reduction on TPOT compared to SoTA baseline ($\textit{i.e.}$ Quest) and at least 50% TPOT reduction compared to full attention on Qwen3-8B and Qwen3-32B models, while matching or surpassing their accuracy on various TTS benchmarks (AIME-24/25, GPQA-Diamond, MATH-500). Our code is available through https://anonymous.4open.science/r/AsyncSpade-063C.

Deep Learning · Large Language Models

Jiapeng Wang, Changxin Tian, Kunlong Chen, ziqi liu, Jiaxin Mao, Xin Zhao, Zhiqiang Zhang, JUN ZHOU

Optimizing data mixtures is is essential for unlocking the full potential of of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy training. To address this, we introduce MergeMix, a novel appraoch that efficiently determines optimal data mixing ratios by repurposing model merging weights as a high-fidelity, low-cost performance proxy. By training domain-specific experts on minimal tokens and optimizing their merging weights against downstream benchmarks, MergeMix effectively optimizes the performance of data mixtures without incurring the cost of full-scale training. Extensive experiments on models with 8B and 16B parameters validate that MergeMix achieves performance comparable to or surpassing exhaustive manual tuning while drastically reducing search costs. Furthermore, MergeMix exhibits high rank consistency (Spearman $\rho > 0.9$) and strong cross-scale transferability, offering a scalable, automated solution for data mixture optimization.

Deep Learning · Robustness

Yunhao Feng, Yifan Ding, Yingshui Tan, Boren Zheng, Yanming Guo, Xiaolong Li, Kun Zhai, Yishan Li, Wenke Huang

Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose \textbf{SkillTrojan}, a backdoor attack that targets skill implementations rather than model parameters or training data. SkillTrojan embeds malicious logic inside otherwise plausible skills and leverages standard skill composition to reconstruct and execute an attacker-specified payload. The attack partitions an encrypted payload across multiple benign-looking skill invocations and activates only under a predefined trigger. SkillTrojan also supports automated synthesis of backdoored skills from arbitrary skill templates, enabling scalable propagation across skill-based agent ecosystems. To enable systematic evaluation, we release a dataset of 3,000+ curated backdoored skills spanning diverse skill patterns and trigger–payload configurations. We instantiate SkillTrojan in a representative code-based agent setting and evaluate both clean-task utility and attack success rate. Our results show that skill-level backdoors can be highly effective with minimal degradation of benign behavior, exposing a critical blind spot in current skill-based agent architectures and motivating defenses that explicitly reason about skill composition and execution. Concretely, on EHR SQL, SkillTrojan attains up to \textbf{97.2\%} ASR while maintaining \textbf{89.3\%} clean ACC on GPT-5.2-1211-Global.