Advanced speech synthesis technologies have enabled highly realistic speech generation, posing security risks that motivate research into audio deepfake detection (ADD). While state space models (SSMs) offer linear complexity, pure causal SSMs architectures often struggle with the content-based retrieval required to capture global frequency-domain artifacts. To address this, we explore the scaling properties of hybrid architectures by proposing XLSR-MamBo, a modular framework integrating an XLSR front-end with synergistic Mamba-Attention backbones. We systematically evaluate four topological designs using advanced SSM variants, Mamba, Mamba2, Hydra, and Gated DeltaNet. Experimental results demonstrate that the MamBo-3-Hydra-N3 configuration achieves competitive performance compared to other state-of-the-art systems on the ASVspoof 2021 LA, DF, and In-the-Wild benchmarks. This performance benefits from Hydra’s native bidirectional modeling, which captures holistic temporal dependencies more efficiently than the heuristic dual-branch strategies employed in prior works. Furthermore, evaluations on the DFADD dataset demonstrate robust generalization to unseen diffusion- and flow-matching-based synthesis methods. Crucially, our analysis reveals that scaling backbone depth effectively mitigates the performance variance and instability observed in shallower models. These results demonstrate the hybrid framework’s ability to capture artifacts in spoofed speech signals, providing an effective method for ADD. Codes are publicly available at https://github.com/saki-ciallo/XLSR-MamBo.
论文检索
输入标题、作者或关键词，从 12,319 篇学术成果中精准定位
The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning
PDF ↗Scaling data and model size has been proven effective for boosting the performance of large language models. In addition to training-time scaling, recent studies have revealed that increasing test-time computational resources can further improve performance. In this work, we introduce Aggregation Fine-Tuning (AFT), a supervised fine-tuning paradigm where the model learns to synthesize multiple draft responses, referred to as proposals, into a single, refined answer, termed aggregation. At inference time, we apply a propose-and-aggregate strategy that iteratively generates and aggregates proposals, effectively scaling inference-time computation without relying on external guidance such as a reward model. Empirical results across benchmark datasets demonstrate that AFT-trained models achieve substantial gains with test-time scaling, outperforming best-of-N baselines while eliminating the need for external reward signals. Notably, an AFT model, fine-tuned from Llama3.1-8B-Base with only 64k data, achieves a 41.3% LC win rate on AlpacaEval 2, surpassing significantly larger LLMs such as Llama3.1-405B-Instruct and GPT-4. By combining sequential refinement and parallel sampling, the propose-and-aggregate framework scales inference-time computation in a flexible manner.
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
PDF ↗The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage. Dataset poisoning offers a proactive defense by reducing the utility of such unauthorized training. However, existing poisoning methods often require full-dataset poisoning and introduce transformations that break code compilability. In this paper, we introduce FunPoison, a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths. FunPoison leverages reusable statement-level templates with automatic repair and conservative safety checking to ensure side-effect freedom, while a type-aware synthesis module preserves type correctness, suppresses static-analysis warnings, and improves stealth. Extensive experiments across multiple CodeLLMs and code-generation benchmarks show that FunPoison achieves effective poisoning by contaminating only 10% of the dataset, while maintaining 100% compilability and functional correctness. FunPoison also remains robust against advanced code sanitization techniques, including detection, purification, rewriting, static-analysis, and formatting defenses.
The core challenge of Compositional Zero-Shot Learning (CZSL) lies in learning representations of sub-concepts (attributes and objects) from seen compositions and recognizing unseen novel compositions. Most existing CZSL methods primarily focus on prompt optimization on the textual side, while overlooking insufficient visual attribute–object sub-concepts disentanglement under a text-centric paradigm. To this end, we propose DMSD, a Dual-Modal Semantic Disentanglement framework that jointly models visual and textual information to achieve effective sub-concept disentanglement. Specifically, DMSD introduces a Contextual Prompt Space, enabling both visual and textual modalities to be modeled under unified contextual semantic representations, thereby enhancing their alignment at the latent semantic level. Moreover, we design Visual Sub-concept Prototypes that explicitly extract and model visual sub-concept features, improving the independence and discriminability of visual sub-concept representations. Furthermore, to achieve fine-grained alignment between visual and textual sub-concepts, we propose a Class-Centroid Bridging Module that guides class centroids toward the textual semantic space, thereby ensuring cross-modal semantic consistency. Extensive experiments on three benchmark datasets (MIT-States, UT-Zappos, and C-GQA) demonstrate that DMSD achieves state-of-the-art performance in both closed-world and open-world settings. Our code is available at https://anonymous.4open.science/r/DMSD-9CC4.
PseudoGD: Enhancing Spatial Reasoning in Vision-Language Models through Pseudo Geometric Knowledge Distillation
PDF ↗Recent Large Vision-Language Models (LVLMs) have shown remarkable success in general semantic understanding. However, they still struggle with 3D spatial reasoning tasks, such as estimating metric distances or understanding precise relative positions. Previous works, like SpatialVLM, tried to address this by using synthesized spatial VQA dataset. However, they are fundamentally limited because their vision encoders are biased toward 2D patterns learned from image-text pairs. In this paper, we argue that this lack of 3D awareness is a critical bottleneck that cannot be solved by data scaling alone. To address this, we propose Pseudo Geometric Distillation (PseudoGD), a framework designed to help vision encoders internalize 3D geometric information using only standard 2D images. PseudoGD explicitly injects metric scale and structural context into the encoder through a Joint Training strategy. This approach optimizes geometric learning and spatial VQA tasks together, ensuring that the Large Language Model (LLM) aligns well with the improved visual features in real-time. Extensive experiments on the OmniSpatial benchmark demonstrate that PseudoGD achieves State-of-the-Art (SOTA) performance across various model architectures. Notably, significant improvements in Hypothetical Perspective Taking and Locate tasks prove that our model has effectively learned a physical sense of space.
As Large Language Models (LLMs) are deployed globally, ensuring their safety and alignment across multiple languages becomes paramount. However, safety behaviors often vary unpredictably between languages, posing significant challenges for consistent and ethical AI. In this work, we systematically investigate the dynamics of multilingual alignment, exploring whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities. We introduce RefusEU a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models. Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.
Neural Processing Units (NPUs) are critical for AI infrastructure, yet developing kernels remains a bottleneck due to the complexity of vendor-specific Domain-Specific Languages (DSLs). While LLMs excel in general coding, they fail to meet the stringent constraints of NPU development, showing a near-zero success rate on complex kernels in our preliminary study. To address these challenges, we present AscendKernelGen, the first comprehensive framework for NPU kernel development, marking a pioneering effort in this field. This framework consists of three interconnected components: (1) Ascend-CoT, the first dataset in the NPU kernel domain that incorporates chain-of-thought reasoning from real-world kernel implementations; (2) KernelGen-LM, a domain-adaptive model trained on this novel dataset using supervised fine-tuning and reinforcement learning; and (3) NPUKernelBench, the first benchmark platform designed to evaluate the compilation, correctness, and performance of generated NPU kernels. Experimental results demonstrate that our approach dramatically bridges the gap in hardware-specific coding: compilation success on complex Level-2 kernels improves from 0% to 95.5% (Pass@10), with 64% functional correctness. AscendKernGen is available at AscendKernGen and NPUKernelBench.
Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated promising gains in enhancing the reasoning capabilities of large language models. However, its dependence on domain-specific verifiers significantly restricts its applicability to open and general domains. Recent efforts such as RLPR have extended RLVR to general domains, enabling training on broader datasets and achieving improvements over RLVR. However, a notable limitation of these methods is their tendency to overfit to reference answers, which constrains the model’s ability to generate diverse outputs. This limitation is particularly pronounced in open-ended tasks such as writing, where multiple plausible answers exist. To address this, we propose DARL, a simple yet effective reinforcement learning framework that encourages the generation of diverse answers within a controlled deviation range from the reference while preserving alignment with it. Our framework is fully compatible with existing general reinforcement learning methods and can be seamlessly integrated without additional verifiers. Extensive experiments on thirteen benchmarks demonstrate overall improvements in reasoning performance. Notably, DARL surpasses RLPR, achieving average gains of 1.3 points on six reasoning benchmarks and 9.5 points on seven general benchmarks, highlighting its effectiveness in improving both reasoning accuracy and output diversity.
Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization
PDF ↗While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO)—searching high-dimensional solution spaces under hard constraints—remains underexplored. To bridge the gap, we introduce NLCO, a **N**atural **L**anguage **C**ombinatorial **O**ptimization benchmark that evaluates LLMs on end-to-end CO reasoning: given a language-described decision-making scenario, the model must output a discrete solution without writing code or calling external solvers. NLCO covers 43 CO problems and is organized using a four-layer taxonomy of variable types, constraint families, global patterns, and objective classes, enabling fine-grained evaluation. We provide solver-annotated solutions and comprehensively evaluate LLMs by feasibility, solution optimality, and reasoning efficiency. Experiments across a wide range of modern LLMs show that high-performing models achieve strong feasibility and solution quality on small instances, but both degrade as instance size grows, even if more tokens are used for reasoning. We also observe systematic effects across the taxonomy: set-based tasks are relatively easy, whereas graph-structured problems and bottleneck objectives lead to more frequent failures. The benchmark dataset and code for data generation and evaluation are publicly available.
Learning with Noisy Labels (LNL) is a challenge where the collected training set can contain incorrect or corrupted labels. Most existing solutions distinguish clean samples from noisy samples and query human experts on noisy samples for denoising. However, these solutions often operate under the unrealistic assumption that the distribution of classes is uniform, overlooking the skewed and imbalanced distributions frequently encountered in real-world scenarios. In this case, we empirically reveal that previous solutions suffer from both selection bias and training bias, leading to distinguish clean samples from noisy samples hardly. In this paper, our work introduces the imbalanced learning with noisy labels (i-LNL) task, which seeks to let the model learn from noisy labels within imbalanced distributions. A new benchmark (ImbaLNL-Bench) comprised of some synthetic and real-world datasets is created to provide a thorough representation of practical use cases. Besides, we propose an innovative collaborative learning framework DeCo for i-LNL tasks. Specifically, we first conduct debiased sample selection, consisting of a robust expert model and a debiased-enhanced threshold strategy, to better separate clean samples from noisy samples, especially for the tail classes. Then we feed selected clean samples to active annotator large language models (LLMs) for re-annotating noisy samples using in-context learning, which can better reduce human effort. Ultimately, we employ distinct loss functions adept at managing subsets with varying degrees of label noise. Extensive experimental results on synthetic and real-world datasets show the effectiveness and superiority of our method.
Benchmarking the Fine-Grained Discriminability in Image-Text Retrieval via Controlled Contrastive Differences
PDF ↗Existing cross-modal image-text retrieval models often retrieve samples with inconsistent details. To evaluate fine-grained discriminability, we introduce MSCOCO-CCD and Flickr30k-CCD, with three key features: (1) a two-level image content taxonomy for contrastive sample generation and fine-grained evaluation; (2) annotation of numerous contrastive samples, where each sample differs from the anchor by a controlled contrastive difference (CCD), with the specific type of difference labeled; (3) a fine-grained contrastive discrimination metric to assess the ability to distinguish fine-grained nuances. Extensive experiments demonstrate that contrastive samples can significantly degrade retrieval performance. Furthermore, fine-grained evaluation reveals that current models still struggle to effectively produce discriminative representations on certain feature types, such as entity emotion and scene attribute. Our datasets and related codes will be publicly released.
Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning
PDF ↗Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance. We observe that better reasoning makes better demonstrations: high-quality solutions serve as more effective in-context examples than low-quality ones. We term this teaching ability Demonstration Utility, and show that the policy model’s own in-context learning ability provides an efficient way to measure it, yielding a quality signal termed Evidence Gain. To leverage this signal during training, we introduce In-Context RLVR, which prepends demonstrations before each rollout. Theoretically, we prove that this simple input modification implicitly reweights rewards by a factor approximately proportional to Evidence Gain, assigning higher weights to high-quality traces without requiring costly computation. Experiments on mathematical reasoning benchmarks demonstrate consistent improvements in both accuracy and reasoning quality over standard RLVR baselines. Our codes and datasets are available at https://github.com/Mithas-114/IC-DAPO.
Most existing Multimodal Sentiment Analysis (MSA) methods rely on holistic fusion, treating all modalities and temporal segments equally. Such strategies often introduce redundant information and obscure the decision process, limiting both robustness and interpretability. Inspired by dual-process theory, we propose FRSR (Fast Retrieval and Slow Reasoning), an interpretable framework that decomposes multimodal sentiment modeling into two cooperative pathways. The Fast Pathway acts as a lightweight evidence selector, using context-aware convolution and auxiliary supervision to retrieve a sparse set of Top-K sentiment-relevant cues from noisy multimodal inputs. Based on these cues, the Slow Pathway performs deeper cross-modal reasoning through learnable reasoning tokens, enabling hierarchical sentiment inference. By separating salient evidence retrieval from multimodal reasoning, FRSR improves interpretability while reducing computational cost. Experiments on three benchmark datasets show that FRSR achieves competitive performance, higher efficiency, stronger robustness to noise, and clearer decision transparency than existing holistic fusion methods.
Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work identifies a fundamental issue in how these models interpret historical artifacts. We define this phenomenon as cultural anachronism, the tendency to misinterpret historical objects using temporally inappropriate concepts, materials, or cultural frameworks. To quantify this phenomenon, we introduce the Temporal Anachronism Benchmark for Vision-Language Models TAB-VLM, a dataset of 600 questions across six categories, designed to evaluate temporal reasoning on 1,600 Indian cultural artifacts spanning prehistoric to modern periods. Systematic evaluations of ten state-of-the-art models reveal significant deficiencies on our benchmark, and even the best model (GPT-5.2) achieves only 58.7% overall accuracy. The performance gap persists across varying architectures and scales, suggesting that cultural anachronism represents a significant limitation in visual AI systems, regardless of model size. These findings highlight the disparity between current VLM capabilities and the requirements for accurately interpreting cultural heritage materials, particularly for non-Western visual cultures underrepresented in training data. Our benchmark provides a foundation for enhancing temporal cognition in multimodal AI systems that interact with historical artifacts. The dataset and code are available in the supplementary material.
User behavior in the real world is diverse, cross-domain, and spans long time horizons. Existing user modeling benchmarks however remain narrow, focusing mainly on short sessions and next-item prediction within a single domain. Such limitations hinder progress toward robust and generalizable user models. We present HORIZON, a new benchmark that reformulates user modeling along three axes i.e. dataset, task, and evaluation. Built from a large-scale, cross-domain reformulation of Amazon Reviews, HORIZON covers 54M users and 35M items, enabling both pretraining and realistic evaluation of models in heterogeneous environments. Unlike prior benchmarks, it challenges models to generalize across domains, users, and time, moving beyond standard missing-positive prediction in the same domain. We propose new tasks and evaluation setups that better reflect real-world deployment scenarios. These include temporal generalization, sequence-length variation, and modeling unseen users, with metrics designed to assess general user behavior understanding rather than isolated next-item prediction. We benchmark popular sequential recommendation architectures alongside LLM-based baselines that leverage long-term interaction histories. Our results highlight the gap between current methods and the demands of real-world user modeling, while establishing HORIZON as a foundation for research on temporally robust, cross-domain, and general-purpose user models.
Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions
PDF ↗Accurately identifying student misconceptions is crucial for personalized education but faces three challenges: (1) data scarcity with long-tail distribution, where authentic student reasoning is difficult to synthesize; (2) fuzzy boundaries between error categories with high annotation noise; (3) deployment paradox—large models overlook unconventional approaches due to pretraining bias and cannot be deployed on edge, while small models overfit to noise. Unlike traditional methods that increase diversity through large-scale data synthesis, we propose a two-stage knowledge distillation framework that mines high-value samples from existing data. The first stage performs standard distillation to transfer task capabilities. The second stage introduces a dual-layer marginal selection mechanism based on cognitive uncertainty, identifying four types of critical samples based on teacher model uncertainty and confidence differences. For different data subsets, we design difficulty-adaptive mechanism to balance hard/soft label contributions, enabling student models to inherit inter-class relationships from teacher soft labels while distinguishing ambiguous error types. Experiments show that with augmented training on only 10.30% of filtered samples, we achieve MAP@3 of 0.9585 (+17.8%) on the MAP-Charting dataset, and using only a 4B parameter model, we attain 84.38% accuracy on cross-topic tests of middle school algebra misconception benchmarks, significantly outperforming sota LLM (67.73%) and standard fine-tuned 72B models (81.25%). Our code is available at https://anonymous.4open.science/r/acl2026_map-5847/.
Long-context understanding poses significant challenges in natural language processing, particularly for real-world dialogues characterized by high redundancy and uneven information density. Although large language models (LLMs) achieve impressive results on existing benchmarks, these datasets fail to reflect the complexities of such texts, limiting their applicability to practical scenarios. To bridge this gap, we construct the first spoken long-text dataset, derived from live streams, designed to reflect the redundancy-rich and conversational nature of real-world scenarios. We construct tasks in three categories: retrieval, reasoning, and hybrid tasks. We then evaluate both popular LLMs and specialized methods to assess their ability to understand long contexts in these tasks. Our results show that current methods exhibit strong task-specific preferences and perform poorly on highly redundant inputs, with no single method consistently outperforming others. We propose a new baseline that better handles redundancy in spoken text and achieves strong performance across tasks. Our findings highlight key limitations of current methods and suggest future directions for improving long-context understanding. Finally, our benchmark fills a gap in evaluating long-context spoken language understanding and provides a practical foundation for developing real-world e-commerce systems. The code and benchmark are available at https://github.com/Yarayx/livelongbench.
Large Language Models demonstrate outstanding performance in many language tasks but still face fundamental challenges in managing the non-linear flow of human conversation. The prevalent approach of treating dialogue history as a flat, linear sequence is misaligned with the intrinsically hierarchical and branching structure of natural discourse, leading to inefficient context utilization and a loss of coherence during extended interactions involving topic shifts or instruction refinements. To address this limitation, we introduce Context-Agent, a novel framework that models multi-turn dialogue history as a dynamic tree structure. This approach mirrors the inherent non-linearity of conversation, enabling the model to maintain and navigate multiple dialogue branches corresponding to different topics. Furthermore, to facilitate robust evaluation, we introduce the Non-linear Task Multi-turn Dialogue (NTM) benchmark, specifically designed to assess model performance in long-horizon, non-linear scenarios. Our experiments demonstrate that Context-Agent enhances task completion rates and improves token efficiency across various LLMs, underscoring the value of structured context management for complex, dynamic dialogues. The dataset and code is available at GitHub.
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives
PDF ↗Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g., generating text not grounded in the audio input. We analyze these grounding failures and identify a distinct taxonomy: Event Omission, False Event Identity, Temporal Relation Error, and Quantitative Temporal Error. To address this, we introduce the AHA (Audio Hallucination Alignment) framework. By leveraging counterfactual hard negative mining, our pipeline constructs a high-quality preference dataset that forces models to distinguish strict acoustic evidence from linguistically plausible fabrications. Additionally, we establish AHA-Eval, a diagnostic benchmark designed to rigorously test these fine-grained reasoning capabilities. We apply this data to align Qwen2.5-Omni. The resulting model, Qwen-Audio-AHA, achieves a 13.7% improvement on AHA-Eval. Crucially, this benefit generalizes beyond our diagnostic set. Our model shows substantial gains on public benchmarks, including 1.3% on MMAU-Test and 1.6% on MMAR, outperforming latest SOTA methods.
Multimodal learning aims to learn unified multimodal representations from heterogeneous modalities and supports many natural language processing tasks. However, multimodal models often exhibit modality laziness: over-relying on a dominant modality and under-exploiting complementary signals. Existing approaches typically strengthen unimodal training or rebalance modality contributions, but they may still emphasize shared semantics and overlook modality-specific cues. To address this, we propose SCOPE, a unified framework for learning complete multimodal representations, achieving Shared-and-COmplementary cue PrEservation. Firstly, SCOPE uses a mutual information-guided disentanglement module to separate shared semantics from modality-specific cues and mitigate representation collapse. Secondly, SCOPE aligns modalities by enforcing structural consistency between modality-wise semantic graphs, avoiding brittle point-wise matching. Finally, SCOPE performs balanced fusion via structure-aware diffusion attention to integrate shared and complementary cues without feature homogenization. Experiments on four benchmark datasets show that SCOPE consistently outperforms SOTA baselines, achieving up to 27.10% accuracy improvement.