Chain-of-Thought (CoT) prompting trades inference speed for reasoning accuracy. Existing compressors force a compromise as static gradient techniques treat tokens independently, severing sequential logic, while uncertainty-based pruning ignores the final answer. We introduce Adaptive GoGI-Skip, a framework that resolves this tension by non-linearly coupling Goal-Gradient Importance (GoGI) with Adaptive Dynamic Skipping (ADS). GoGI quantifies each token's functional contribution to answer correctness via gradient sensitivity. ADS leverages runtime entropy to dynamically modulate the GoGI threshold, preserving low-gradient tokens essential for structural coherence at high-uncertainty junctions. Trained on 7,472 MATH traces, our policy transfers zero-shot to AIME, GPQA, and GSM8K, reducing token volume by >45% and accelerating inference up to 2.0x without accuracy loss. These results suggest that thinking-optimal compression demands synergy between teleological goals and epistemic uncertainty.
论文检索
输入标题、作者或关键词，从 15,207 篇学术成果中精准定位
Many semantics for abstract weighted argumentation assume that each argument is associated with a numerical initial weight. Eliciting these initial weights poses several challenges: (1) accurately providing a specific numerical value is often difficult, and (2) individuals frequently confuse initial weights with acceptability degrees in the presence of other arguments. We therefore propose an elicitation pipeline that allows a user to specify their believed final acceptability degree intervals for each argument. We can determine which portion (if any) of these intervals are rational, refining the intervals, or restoring rationality when the intervals are irrational. This allows us to ultimately identify possible initial weights for each argument.
Real-time clustering of dynamic multi-view data streams is a critical yet challenging task in open-world applications. While several methods have been proposed to address this task, most of them extract features incrementally but fail to output instant clustering results for the current batch. In addition, they neglect semantic consistency, causing the cluster labels of identical concepts to drift unpredictably due to independent processing. To address these limitations, we propose a real-time semantic consistent incremental multi-view clustering framework. Specifically, we constructs a compact historical knowledge base via an adaptive diversity-aware selection mechanism, which guides the clustering of incoming data, enabling immediate inference without accessing the full history. Furthermore, we introduce a semantic alignment strategy based on consensus centers to ensure robust label consistency over time. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method.
Automated radiology report generation aims to create clear and clinically correct diagnostic reports from medical images. Existing retrieval enhancement methods primarily focus on reusing textual knowledge, neglecting the crucial role of local visual pattern memory in clinical diagnosis. Furthermore, cross-modal retrieval lacking explicit clinical semantic constraints can easily introduce irrelevant pathological information, thereby reducing the clinical effectiveness of the generated reports. To address these challenges, we propose ClinAlign—a memory-based retrieval framework aligned with clinical workflow, drawing inspiration from clinical diagnostic workflows. Visually, we construct a disease-aware visual memory bank and enhance local patch representations through proposed Memory‑based Patch Pattern Augmentation (MPPA), thereby improving the perception and discrimination of pathological regions. On the textual side, we construct a disease-aware textual memory bank and introduce Classification-Guided Prompt Augmentation (CGPA), where disease state predictions are converted into structured diagnostic prompts to provide explicit semantic guidance for textual memory retrieval.Extensive experiments on two medical report generation benchmarks, MIMIC-CXR and IU X-Ray, demonstrate the effectiveness and practical value of our proposed method.
Brain effective connectivity (EC) characterizes directional causal interactions among brain regions. However, learning stable and directionally explicit EC networks from multimodal data remains challenging. In practice, functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) differ substantially in spatio-temporal resolution and noise characteristics. Existing methods often rely on manual spatio-temporal alignment and tend to recover only partial causal structures under high noise and Bayesian equivalence classes. To address these challenges, we propose a spatio-temporal constrained Bayesian causal network for multimodal brain effective connectivity learning (STCBN-EC). First, STCBN-EC constructs an anatomically guided EEG–fMRI spatial mapping and derives a unified spatio-temporal representation through slice-level alignment and adaptive modality fusion. Then, a Bayesian causal network is employed to model nonlinear inter-regional dependencies, where uncertainty-driven surrogate scoring is used to evaluate candidate structures. Finally, multimodal representation learning and EC structure estimation are jointly optimized via a gradient-free global optimization strategy. Experiments on simulated and real EEG–fMRI datasets demonstrate that STCBN-EC outperforms state-of-the-art methods and effectively captures state-dependent directional interactions among brain regions.
Diffusion policy has shown impressive performance in robotic manipulation tasks while struggling with out-of-distribution shifts and limited demonstrations. Recent advances primarily focus on improving geometric or perceptual representations for diffusion policy. However, these approaches rely heavily on instantaneous observations, making them vulnerable when visual inputs deviate from the training distribution. Our key insight is that robust generalization in diffusion policy requires both structured reasoning over skill compositions and an explicit memory mechanism for accumulating and reusing learned policy knowledge. To this end, we propose "raise one and infer three" diffusion policy (ROITDP), a novel approach that introduces two complementary mechanisms. First, we propose a reasoning mechanism built upon the Chain-of-Skill Noise Watermark, which encodes skill-level reasoning graph representations into the initial noise space, thereby enabling temporally coherent multi-step reasoning throughout the diffusion process under distribution shifts. We further introduce a memory mechanism in the form of a Self-evolving Policy Knowledge Bank that discretizes spatio-temporally refined trajectories into reusable skill primitives via a VQ-VAE architecture, providing adaptive memory to guide and refine action generation. Extensive experimental results on both simulated and real-world environments demonstrate the superiority and robustness of our method.
Class-Incremental Learning (CIL) aims to enable models to sequentially learn new tasks while retaining knowledge from previous ones. Recently, merging-based pre-trained CIL methods have gained significant attention due to their competitive performance and high inference efficiency. However, most existing approaches decouple training from merging, neglecting the compatibility among task-specific adapters. This incompatibility introduces severe conflicts during integration, resulting in catastrophic forgetting and notable performance degradation. To address this limitation, we propose MOBO, a Merging-Oriented Bi-Level Optimization framework that synergizes the optimization of the current task model with the performance of the final merged model. At the upper level, we introduce a global loss that anticipates the merged model's behavior, guiding the current task parameters toward a solution space that facilitates effective merging. At the lower level, we employ a dynamic weighted merging strategy to optimize merging coefficients and update the merged model. By alternately optimizing the task-specific and merged models, MOBO effectively mitigates the performance loss caused by incompatible adapter integration. Comprehensive experiments on CIFAR-100, CUB-200, ImageNet-R, ImageNet-A, and VTAB demonstrate the superiority of our approach, highlighting its robustness and scalability, particularly on long task sequences.
Context-Aware Multi-Agent Coordination: Learning Correlated Equilibria Under Situational Constraints
Effective multi-agent coordination requires aligning incentives while adhering to complex requirements. However, real-world systems often impose situational constraints, context-dependent requirements triggered only under specific conditions, which challenge standard Correlated Equilibria (CE) solutions. We propose Situational-Constrained Density-Based Correlated Equilibria (SC-DBCE), a novel concept in Markov Games that formalizes situational constraints as logic implications. To solve this, we introduce Situational-Constrained Correlated Policy Iteration (SC-CPI), a reinforcement learning algorithm employing a smooth Log-Sum-Exp mechanism for constraint optimization. Evaluations on multi-agent games, smart grids, and warehouse robotics demonstrate that SC-CPI consistently outperforms baselines in both equilibrium quality and constraint adherence. To our knowledge, this is the first method learning CE under situational constraints.
Tool-augmented methods aim to enhance the reasoning capabilities of large language models (LLMs) by invoking external tools, which can be broadly categorized into training-free and training-based methods. Training-free methods can directly instruct LLMs to invoke external tools, but they exhibit limited generalization in dynamic environments. In contrast, training-based methods use a teacher model to generate tool-use trajectories and fine-tune a student model to distill the trajectories that can generalize across tasks. However, they still face two major challenges: (1) Knowledge boundary mismatch: teacher trajectories may contain steps that the student cannot execute without tools due to their mismatch of knowledge boundaries. (2) Tool overuse propagation: the student inherits the misaligned tool-use strategy from teacher model. To address these challenges, we propose RADAR, an automated framework for knowledge boundary discovery and tool overuse mitigation. First, RADAR performs semantic anchoring to select representative seeds. Second, simulated annealing probing is employed to actively explore the student model’s tool-use boundary and acquire sparse, verified student-aware labels. Third, it globally propagates these labels and rewrites conflicts, yielding deployment-aligned decisions with fewer unnecessary tool calls. We conduct experiments on multiple benchmarks, compared to SOTA method, RADAR reduces average tool-use by 52.7% while improving accuracy by 3.2% across three models.
The increasing availability of trajectory data is often hampered by sparsity and noise. Existing trajectory recovery methods are further limited by either information loss from coordinate discretization into location IDs, or the inefficiency of conventional diffusion models that require a lengthy denoising process from pure noise. To address these challenges, we propose DiffVec, a novel and efficient diffusion framework for free-space trajectory recovery that operates directly on continuous coordinate data. The backbone of our framework is MVformer, a Transformer-based architecture that models motion vectors—the differences between consecutive coordinates—to better capture the local motion patterns of movement. This model is trained within our ResTraj diffusion paradigm, which commences the denoising process from a structured, interpolated prior to significantly reduce sampling steps. Extensive experiments on the Geolife and Porto datasets demonstrate that DiffVec significantly outperforms state-of-the-art baselines across MAE, MSE, and NDTW.
Open cross-domain federated graph learning facilitates collaborative learning among clients from distinct graph domains while preserving privacy. However, severe structure and feature heterogeneity in open scenarios exacerbates the multiplicative amplification of structural and feature noises within graph neural network encoders, leading to significant negative transfer. Existing methods addressing partial heterogeneity are insufficient. We theoretically reveal this amplification mechanism and propose a novel learning method FedFINFO, which leverages full-informativeness shared knowledge. Specifically, we construct an aligned and general feature space integrating node semantic and structural roles. We proposed a counterfactual multi-view framework to explicitly learn a structure masker for extracting consensus subgraphs. These jointly suppress the mutual amplification of noises at the source. We also propose a history-aware adaptive multi-channel aggregation mechanism to enable dynamic and personalized sharing driven by channel similarity while preventing collaborative oscillation. FedFINFO effectively reconciles common knowledge sharing with personalized knowledge retention, significantly mitigating negative transfer. Extensive experiments under cross-dataset and cross-domain settings demonstrate the superiority of our method.
Multi-step retrosynthetic planning aims to decompose target molecules into available starting materials by iteratively invoking single-step prediction models within a search algorithm. The success of retrosynthetic planning depends on the joint guidance of single-step reasoning and global search across steps. However, most existing frameworks make step-wise decisions based only on the current molecular state, without explicitly modeling synthesizability signals that reflect long-range reachability. In this work, we propose GuideRetro, a synthesizability-aware framework for multi-step retrosynthetic planning that integrates global synthesizability knowledge into step-wise retrosynthetic prediction. GuideRetro learns transferable knowledge from large-scale reaction networks by modeling the evolution of synthetic complexity along reaction pathways. During planning, a route-aware synthesis state modeling module combines the evolving retrosynthetic route with retrieved global signals to guide reactant generation at each step. Experiments on benchmark datasets show that GuideRetro achieves state-of-the-art performance. The integration of global synthesizability knowledge and route-aware modeling improves planning accuracy and search efficiency under realistic retrosynthetic settings. The code is available at: https://github.com/L-AJ/GuideRetro.
Target speaker extraction (TSE) aims to extract the speech of a target speaker from mixtures containing multiple competing speakers. Conventional TSE systems predominantly rely on speaker cues, such as pre-enrolled speech, to identify and isolate the target speaker. However, in many practical scenarios, clean enrollment utterances are unavailable, limiting the applicability of existing approaches. In this work, we propose DAE-TSE, a keyword-guided TSE framework that specifies the target speaker through distinct keywords they utter. By leveraging keywords (i.e., partial transcriptions) as cues, our approach provides a flexible and practical alternative to enrollment-based TSE. DAE-TSE follows the Detect-Attend-Extract (DAE) paradigm: it first detects the presence of the given keywords, then attends to the corresponding speaker based on the keyword content, and finally extracts the target speech. Experimental results demonstrate that DAE-TSE outperforms standard TSE systems that rely on clean enrollment speech. To the best of our knowledge, this is the first study to utilize partial transcription as a cue for specifying the target speaker in TSE, offering a flexible and practical solution for real-world scenarios. Our code (https://github.com/GnafiY/DAE-TSE) and demo page (https://gnafiy.github.io/DAE-TSE_demo) are now publicly available.
Adaptive Learning Systems (ALS) play a key role in promoting the equity of education, which can provide personalized teaching on a large scale. However, the existing question recommendation methods face the problem of data sparsity at the scenario of cold-start, and lack the ability of long-term teaching reasoning. To address these challenges, we propose QuesRecAgent, a multi-agent framework which involves Large Language Models (LLMs) and the Relexion mechanism for adaptive question recommendation. Different from the traditional black-box methods, the QuesRecAgent applies a framework Dual-Loop State Decoupling architecture, which achieves a rapid updating of beliefs through simulated interaction in the inner loop and do the authoritative diagnosis and meta-strategy reflection to optimize the teaching strategy in the outer loop. Furthermore, with the support of a Topological Knowledge Graph (TKG) and the theory of Zone of Proximal Development (ZPD), the QuesRecAgent ensures a high-quality learning guidance even facing students with limited interaction records. Our experiments on three real-world datasets show that the QuesRecAgent outperforms state-of-the-art baselines in total knowledge gain and other metrics, providing a robust and interpretable solution for promoting high-quality personalized education.
We examine how causal beliefs affect an agent's choices and how feedback on those choices leads to updated causal beliefs. Building on the structural-equations framework for modeling causality, we first examine the general problem of updating causal beliefs in the face of novel (and possibly inexplicable) data. We model an agent who is uncertain of the true causal model, and therefore entertains a probabilistic belief over the set of possible models. We then consider how causal beliefs influence choices by building a model of agency and utility on top of the usual structural-equations framework. Using these two components, we propose a notion of steady state, where the feedback received from an agent's optimal action, given her current beliefs about the true causal model, can be rationalized by those beliefs.
C-RASP is a simple programming language that was recently shown to capture concepts expressible by transformers. In this paper, we develop new algorithmic techniques for automatically verifying C-RASPs. To this end, we establish a connection to the verification of synchronous dataflow programs in Lustre, which enables us to exploit state-of-the-art model checkers utilizing highly optimized SMT-solvers. Our second contribution addresses learning a C-RASP program in the first place. To this end, we provide a new algorithm for learning a C-RASP from examples using local search. We demonstrate efficacy of our implementation for benchmarks of C-RASPs in the literature, in particular in connection to the following applications: (1) transformer program optimization, and (2) constrained learning of transformer programs (based on a partial specification).
Combinatorial and optimization problems are fundamental to many industrial AI applications. Solving large-scale real-world instances of such problems typically requires careful problem formalization, specialized solvers, and expert-designed heuristics. Thus, experts need to specify not only *what* solutions are, but also *how* they are derived. By introducing the tool CheckMate, we show that algorithm generation via code evolution represents a paradigm shift by eliminating the need to formulate the *how*. CheckMate solely relies on the *what*. Specifically, a formal specification ensures solutions' correctness and enables systematic performance evaluation of the generated programs, while a natural language description guides the evolutionary process. The effectiveness of our method is demonstrated on selected problems from two industrial domains: configuration and scheduling. In all cases, the evolved algorithms consistently outperform state-of-the-art solvers. This underscores the potential of formal methods in guiding code evolution for automatically solving complex real-world problems.
Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data poisoning. In this work, we reveal that backdoor behaviors tend to be absorbed by a simpler parallel branch when jointly trained with the main network. Motivated by this insight, we propose Trapping and Removing (TR), a simple yet effective training-time defense that introduces a lightweight shortcut branch as a “honeypot” to trap backdoor knowledge. After training, backdoors can be removed by discarding the shortcut, without requiring any additional data. To further enhance backdoor isolation while maintaining benign performance, we design a knowledge decoupling strategy with entropy-based weight assignment, encouraging poisoned samples to flow through the honeypot while guiding the main network to focus on benign learning. In addition, we introduce an automatic shortcut generation strategy to improve generalization across model architectures. Extensive experiments on four benchmark datasets and five model architectures demonstrate that our approach effectively mitigates a wide range of backdoor attacks while preserving performance on benign data. Code: github.com/Zixuan-Zhu/TR.
Supervised proxy-based deep cross-modal hashing has become the dominant paradigm for large-scale retrieval. However, prevalent methods model class proxies as deterministic points in the embedding space. This rigid assumption causes severe gradient conflicts in multi-label scenarios, where gradient conflicts arising from label co-occurrence lead to severe gradient contention and optimization collapse.To resolve this, we propose Kent-based Distributional Proxy Hashing (KDPH), a novel framework that shifts proxy representation from static points to flexible anisotropic Kent distributions on the hypersphere. Unlike point proxies that must shift their positions to accommodate conflicting gradients, KDPH absorbs these conflicts by dynamically adjusting its directional variance. This allows the proxy to maintain a stable semantic mean direction while stretching to cover diverse label correlations. Furthermore, to ensure stable training of these geometric parameters, we derive a tailored loss function incorporating the Cayley transform to enforce strict orthogonality. To the best of our knowledge, KDPH is the first framework to successfully introduce the Kent distributions into cross-modal hashing.Experiments on three benchmark datasets demonstrate that KDPH mitigates proxy collapse and chaotic oscillation, significantly outperforms state-of-the-art methods. Code is available at https://github.com/Senmo996/KDPH-official-code.
Source-Fully-Free Domain Adaptation (SFF-DA) has emerged as a strategic paradigm to adapt Vision-Language Models (VLMs) without any access to source data or task-specific source models. However, we identify a critical "Dual Semantic Drift" that hinders this process: static drift caused by the stagnation of frozen hand-crafted templates, and dynamic drift resulting from noisy, instance-level generated captions. These issues lead to a severe stability-plasticity dilemma, manifesting as semantic misalignment and class collapse. To address this, we propose DSSG (Dual-Stream Semantic Guidance), an end-to-end framework that reconciles fine-grained plasticity with global stability. Our core contribution is the Dual Semantic Guidance (DSG) module, which integrates a captioning stream for detailed domain nuances with a template stream to anchor global categorical consistency. Furthermore, a Dynamic Cross-Modal Knowledge Distillation (CMKD) module is introduced to adaptively optimize teacher-student alignment across modalities. Extensive experiments demonstrate that DSSG significantly outperforms current state-of-the-art methods across multiple benchmarks, providing a robust solution for the unsupervised transfer of foundation models. The code is available on https://github.com/mrmenand/DSSG.