Speech inherently contains rich acoustic information that extends far beyond the textual language. In real-world spoken communication, effective interpretation often requires integrating semantic meaning (e.g., content), paralinguistic features (e.g., emotions, speed, pitch) and phonological characteristics (e.g., prosody, intonation, rhythm), which are embedded in speech. While recent multimodal Speech Large Language Models (SpeechLLMs) have demonstrated remarkable capabilities in processing audio, their ability to perform fine-grained perception and complex reasoning in natural speech remains largely unexplored. To address this gap, we introduce MMSU, a comprehensive benchmark designed specifically for understanding and reasoning in speech. MMSU comprises 5,000 meticulously curated audio-question-answer triplets across 47 distinct tasks. Notably, linguistic theory forms the foundation of speech language understanding (SLU), yet existing benchmarks have paid insufficient attention to this fundamental aspect and fail to capture the broader linguistic picture. To ground our benchmark in linguistic principles, we systematically incorporate a wide range of linguistic phenomena, including phonetics, prosody, rhetoric, syntactics, semantics, and paralinguistics. Through a rigorous evaluation of 22 advanced SpeechLLMs, we identify substantial room for improvement in existing models. MMSU establishes a new standard for comprehensive assessment of SLLU, providing valuable insights for developing more sophisticated human-AI speech interaction systems.
论文检索
输入标题、作者或关键词，从 7,537 篇学术成果中精准定位
Deep Learning · Generative Models and Autoencoders
Reward models are crucial for aligning large language models (LLMs) with human values and intentions. Existing approaches follow either Generative (GRMs) or Discriminative (DRMs) paradigms, yet both suffer from limitations: GRMs typically demand costly point-wise supervision, while DRMs produce uncalibrated relative scores that lack probabilistic interpretation. To address these challenges, we introduce a novel reward modeling paradigm: Probabilistic Reward Model (PRM). Instead of modeling reward as a deterministic scalar, our approach treats it as a random variable, learning a full probability distribution for the quality of each response. To make this paradigm practical, we present its closed-form, discrete realization: the **Ordinal Probabilistic Reward Model** (OPRM), which discretizes the quality score into a finite set of ordinal ratings. Building on OPRM, we propose a data-efficient training strategy called **Region Flooding Tuning** (RgFT). It enables rewards to better reflect absolute text quality by incorporating quality-level annotations, which guide the model to concentrate the probability mass within corresponding rating sub-regions. Experiments on various reward model benchmarks show that our method improves accuracy by **2.9% ～ 7.4%** compared to prior reward models, demonstrating strong performance and data efficiency. Analysis of the score distribution provides evidence that our method captures not only relative rankings but also absolute quality.
Applications · Everything Else
With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem requires fine-grained reasoning to accurately assess the relevance between the task and each candidate document. This capability, however, poses a significant challenge for existing IR techniques. Despite recent progress in reasoning-enhanced IR, existing approaches still face significant challenges in applicability, scalability, and efficiency. In this work, we propose **Retro\***, a novel approach for reasoning-intensive document retrieval. Our method introduces a rubric-based relevance **scoring mechanism**, enabling the model to reason about the relationship between a task and a document based on explicitly defined criteria, whereby producing a fine-grained, interpretable relevance score. Retro\* also supports **test-time scaling** by combining multiple reasoning trajectories via score integration, which produces more reliable relevance estimates. To optimize Retro\*'s reasoning capabilities, we introduce a novel **reinforcement learning** algorithm tailored for its relevance scoring mechanism, which employs two composite rewards to fully exploit the trajectories of each training sample. Our experiments show that Retro\* outperforms existing document retrieval methods with notable advantages, leading to **state-of-the-art** performance on the BRIGHT benchmark.
Deep Learning · Algorithms
Dataset distillation (DD) has emerged as a promising approach to compress datasets and speed up model training. However, the underlying connections among various DD methods remain largely unexplored. In this paper, we introduce UniDD, a spectral filtering framework that unifies diverse DD objectives. UniDD interprets each DD objective as a specific filter function applied to the eigenvalues of the feature-feature correlation (FFC) matrix to extract certain frequency information of the feature-label correlation (FLC) matrix. In this way, UniDD reveals that the essence of DD fundamentally lies in matching frequency-specific features. Moreover, we characterize the roles of different filters. For example, low-pass filters, \eg, DM and DC, capture blurred patches, while high-pass filters, \eg, MTT and FrePo, prefer to synthesize fine-grained textures and have better diversity. However, existing methods can only learn the sole frequency information as they rely on fixed filter functions throughout distillation. To address this limitation, we further propose Curriculum Frequency Matching (CFM), which gradually adjusts the filter parameter to cover both low- and high-frequency information of the FFC and FLC matrices. Extensive experiments on small-scale datasets, such as CIFAR-10/100, and large-scale ImageNet-1K, demonstrate the superior performance of CFM over existing baselines and validate the practicality of UniDD.
Deep Learning · Theory
Transformer components such as non-linear activations and normalization are inherently non-injective, suggesting that different inputs could map to the same output and prevent exact recovery of the input from a model’s representations. In this paper, we challenge this view. First, we prove mathematically that transformer language models mapping discrete input sequences to their corresponding sequence of continuous representations are injective and therefore lossless, a property established at initialization and preserved during training. Second, we confirm this result empirically through billions of collision tests on six state-of-the-art language models, and observe no collisions. Third, we operationalize injectivity: we introduce SipIt, the first algorithm that provably and efficiently reconstructs the exact input text from hidden activations, establishing linear-time guarantees and demonstrating exact invertibility in practice. Overall, our work establishes injectivity as a fundamental and exploitable property of language models, with direct implications for transparency, interpretability, and safe deployment.
Accurate cell instance segmentation is foundational for digital pathology analysis. Existing methods based on contour detection and distance mapping still face significant challenges in processing complex and dense cellular regions. Graph coloring-based methods provide a new paradigm for this task, yet the effectiveness of this paradigm in real-world scenarios with dense overlaps and complex topologies has not been verified. Addressing this issue, we release a large-scale dataset GBC-FS 2025, which contains highly complex and dense sub-cellular nuclear arrangements. We conduct the first systematic analysis of the chromatic properties of cell adjacency graphs across four diverse datasets and reveal an important discovery: most real-world cell graphs are non-bipartite, with a high prevalence of odd-length cycles (predominantly triangles). This makes simple 2-coloring theory insufficient for handling complex tissues, while higher-chromaticity models would cause representational redundancy and optimization difficulties. Building on this observation of complex real-world contexts, we propose Disco (Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring), an adjacency-aware framework based on the “divide and conquer” principle. It uniquely combines a data-driven topological labeling strategy with a constrained deep learning system to resolve complex adjacency conflicts. First, “Explicit Marking” strategy transforms the topological challenge into a learnable classification task by recursively decomposing the cell graph and isolating a “conflict set.” Second, “Implicit Disambiguation” mechanism resolves ambiguities in conflict regions by enforcing feature dissimilarity between different instances, enabling the model to learn separable feature representations. Disco achieves a significant 7.08\% improvement in the PQ metric on the GBC-FS 2025 dataset and an average improvement of 2.72% across all datasets. Furthermore, the predicted “Conflict Map” serves as a novel tool for interpreting topological complexity, offering new potential for data-driven pathology research.
Social Aspects · Accountability, Transparency and Interpretability
Uncovering the opacity of diffusion-based generative models is urgently needed, as their applications continue to expand while their underlying procedures largely remain a black box. With a critical question -- how can the diffusion generation process be interpreted and understood? -- we proposed *Patronus*, an interpretable diffusion model that incorporates a prototypical network to encode semantics in visual patches, revealing *what* visual patterns are learned and *where* and *when* they emerge throughout denoising. This interpretability of Patronus provides deeper insights into the generative mechanism, enabling the detection of shortcut learning via unwanted correlations and the tracing of semantic emergence across timesteps. We evaluate *Patronus* on four natural image datasets and one medical imaging dataset, demonstrating both faithful interpretability and strong generative performance. With this work, we open new avenues for understanding and steering diffusion models through prototype-based interpretability. Our code is available at [nina-weng.github.io/patronus.github.io](https://nina-weng.github.io/patronus.github.io/).
Deep Learning · Everything Else
Chess has played a uniquely important role as a testbed domain for artificial intelligence. Applying new architectures to improve absolute chess performance, and more recently to predict human moves at specified skill levels, has therefore garnered attention in the machine learning literature. Current approaches to these problems employ transformer models with widely varying architectural designs, and use unintuitive tokenization schemes that are not amenable to interpretability techniques, which hinders their applicability for teaching and human-AI interaction. We introduce Chessformer, a novel chess transformer model design that consists of an encoder-only model which processes chessboard squares as input tokens, instead of moves or the entire position, a dynamic positional encoding scheme that allows the model to flexibly adapt to the unique geometries present in chess, and an attention-based policy output design. We show that Chessformer advances the state of the art in all three major chess modeling goals: it significantly improves the chess-playing performance of a state-of-the-art chess engine, it surpasses the previous best human move-matching prediction performance with a much smaller model, and it enables substantial interpretability benefits. Our unified approach constitutes a broad advance across several important tasks in chess AI, and also demonstrates the benefits of carefully adapting transformers' tokenization systems, output systems, and positional encodings to reflect the structure of a domain of interest.
Applications · Physics
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively underexplored. Most existing physics benchmarks evaluate only final answers, which fail to capture reasoning processes, while recent stepwise methods rely on heuristic LLM-as-judge scoring or restrictive linear assumptions, limiting reliability and diagnostic validity. We introduce PRISM-Physics, a process-level evaluation framework and benchmark for complex physics reasoning problems. Solutions are represented as directed acyclic graphs (DAGs) of formulas, explicitly encoding causal dependencies among intermediate steps to enable fine-grained, interpretable, and theoretically grounded scoring. We prove the optimality of the DAG representation and the corresponding scoring policy. Combining with a fully rule-based method for symbolic formula equivalence matching that we developed, we ensure consistent validation across diverse formulations without heuristic judgments. Results show that our evaluation framework is more aligned with human experts' scoring. Experiments on state-of-the-art LLMs reveal persistent reasoning failures in physics, while step-level scoring offers both diagnostic insight and rich signals for later training. By combining structural rigor, theoretical guarantees, and symbolic validation, PRISM-Physics provides a principled foundation for advancing process-level evaluation and guiding the development of models with deeper scientific reasoning capabilities.
Computer Vision · Image and Video Generation
Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal intelligence. However, the community still lacks a rigorous reasoning-centric benchmark to systematically evaluate the alignment between understanding and generation, and their generalization potential in complex visual tasks. To this end, we introduce \textbf{GIR-Bench}, a comprehensive benchmark that evaluates unified models across three complementary perspectives. Firstly, we explore whether models can consistently leverage the same knowledge for both understanding and generation (GIR-Bench-Uni). Secondly, we investigate whether models can perform reasoning-centric text-to-image generation that requires applying logical constraints and implicit knowledge to generate faithful visual content (GIR-Bench-T2I). Thirdly, we evaluate whether models can handle multi-step reasoning in editing (GIR-Bench-Edit). For each subset, we carefully design different task-specific evaluation pipelines tailored for each task. This enables fine-grained and interpretable evaluation while mitigating biases from the prevalent MLLM-as-a-Judge paradigm. Extensive ablations over various unified models and generation-only systems have shown that: Although unified models are more capable of reasoning-driven visual tasks, they still exhibit a persistent gap between understanding and generation. The data and code for GIR-Bench are available at \url{https://anonymous.4open.science/r/GIR-Bench-7E40}.
Computer Vision · Vision Models & Multimodal
As vision-language models (VLMs) become increasingly integrated into daily life, the need for accurate visual culture understanding is becoming critical. Yet, these models frequently fall short in interpreting cultural nuances effectively. Prior work has demonstrated the effectiveness of retrieval-augmented generation (RAG) in enhancing cultural understanding in text-only settings, while its application in multimodal scenarios remains underexplored. To bridge this gap, we introduce RAVENEA (Retrieval-Augmented Visual culturE uNdErstAnding), a new benchmark designed to advance visual culture understanding through retrieval, focusing on two tasks: culture-focused visual question answering (cVQA) and culture-informed image captioning (cIC). RAVENEA extends existing datasets by integrating over 11,396 unique Wikipedia documents curated and ranked by human annotators. Through the extensive evaluation on seven multimodal retrievers and fifteen VLMs, RAVENEA reveals some undiscovered findings: (i) In general, cultural grounding annotations can enhance multimodal retrieval and corresponding downstream tasks. (ii) VLMs, when augmented with culture-aware retrieval, generally outperform their non-augmented counterparts (by averaging +6% on cVQA and +11% on cIC). (iii) Performance of culture-aware retrieval augmented varies widely across countries. These findings highlight the limitations of current multimodal retrievers and VLMs, underscoring the need to enhance visual culture understanding within RAG systems. We believe RAVENEA offers a valuable resource for advancing research on retrieval-augmented visual culture understanding.
Computer Vision · Vision Models & Multimodal
Videos, with their unique temporal dimension, demand precise grounded understanding, where answers are directly linked to visual, interpretable evidence. Despite significant breakthroughs in text-based reasoning with large language models, multi-modal reasoning - especially for videos - remains limited. In this work, we fill this gap by introducing VideoMind, a novel video-language agent for temporal-grounded video reasoning. Our method involves two key innovations: (1) We identify four essential capabilities for grounded video reasoning and propose a role-based agentic workflow, comprising a planner to coordinate roles, a grounder for temporal event localization, a verifier to assess event candidates, and an answerer for question answering. (2) To efficiently integrate these roles during inference, we propose a novel Chain-of-LoRA mechanism, where a unified base model with multiple LoRA adapters is leveraged to enable seamless role switching, balancing efficiency and flexibility. Extensive experiments on 15 benchmarks across Grounded VideoQA, Video Temporal Grounding, and General VideoQA tasks demonstrate the effectiveness of the proposed scheme in advancing video agent, test-time scaling, and long-form video reasoning. Code, models, datasets, and demos are available at https://videomind.github.io/.
SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation
Applications · Genetics, Cell Biology, Health, etc
Large language models (LLMs) are increasingly applied in scientific research, offering new capabilities for knowledge discovery and reasoning. In single-cell biology, however, evaluation practices for both general and specialized LLMs remain inadequate: existing benchmarks are fragmented across tasks, adopt formats such as multiple-choice classification that diverge from real-world usage, and rely on metrics lacking interpretability and biological grounding. We present **SC-ARENA**, a natural language evaluation framework tailored to single-cell foundation models. SC-ARENA formalizes a *virtual cell* abstraction that unifies evaluation targets by representing both intrinsic attributes and gene-level interactions. Within this paradigm, we define five natural language tasks — cell type annotation, captioning, generation, perturbation prediction, and scientific QA — that probe core reasoning capabilities in cellular biology. To overcome the limitations of brittle string-matching metrics, we introduce **knowledge-augmented evaluation**, which incorporates external ontologies, marker databases, and scientific literature to support biologically faithful and interpretable judgments. Experiments and analysis across both general-purpose and domain-specialized LLMs demonstrate that: (i) under the *Virtual Cell* unified evaluation paradigm, current models achieve uneven performance on biologically complex tasks, particularly those demanding mechanistic or causal understanding; and (ii) our knowledge-augmented evaluation framework ensures biological correctness, provides interpretable, evidence-grounded rationales, and achieves high discriminative capacity, overcoming the brittleness and opacity of conventional metrics. **SC-ARENA** thus provides a unified and interpretable framework for assessing LLMs in single-cell biology, pointing toward the development of biology-aligned, generalizable foundation models.
Deep Learning · Everything Else
Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresponding model weight changes ("weight diffs") are not generally interpretable. While inspecting the finetuning dataset can give a sense of how the model might have changed, these datasets are often not publicly available or are too large to work with directly. Towards the goal of broadly understanding model weight changes in natural language, we introduce Diff Interpretation Tuning (DIT), a method that trains models to describe their own finetuning-induced modifications. Our approach uses synthetic, labeled weight diffs to train an introspection adapter, which can be applied to a compatible finetuned model to make it self-describe the weight changes. We demonstrate in two proof-of-concept settings (reporting hidden behaviors and summarizing finetuned knowledge) that our method enables models to describe their finetuning-induced modifications using concise and accurate natural language descriptions.
Social Aspects · Accountability, Transparency and Interpretability
Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague, inconsistent, and require manual relabeling. In response, we introduce *semantic regexes*, structured language descriptions of LLM features. By combining primitives that capture linguistic and semantic patterns with modifiers for contextualization, composition, and quantification, semantic regexes produce precise and expressive feature descriptions. Across quantitative benchmarks and qualitative analyses, semantic regexes match the accuracy of natural language while yielding more concise and consistent feature descriptions. Their inherent structure affords new types of analyses, including quantifying feature complexity across layers, scaling automated interpretability from insights into individual features to model-wide patterns. Finally, in user studies, we find that semantic regexes help people build accurate mental models of LLM features.
Deep Learning · Everything Else
In human society, collective decision making has often outperformed the judgment of individuals. Classic examples range from estimating livestock weights to predicting elections and financial markets, where averaging many independent guesses often yields results more accurate than experts. These successes arise because groups bring together diverse perspectives, independent voices, and distributed knowledge, combining them in ways that cancel individual biases. This principle, known as the Wisdom of Crowds, underpins practices in forecasting, marketing, and preference modeling. Large Language Models (LLMs), however, typically produce a single definitive answer. While effective in many settings, this uniformity overlooks the diversity of human judgments shaping responses to ads, videos, and webpages. Inspired by how societies benefit from diverse opinions, we ask whether LLM predictions can be improved by simulating not one answer but many. We introduce Social Agents, a multi-agent framework that instantiates a synthetic society of human-like personas with diverse demographic (e.g., age, gender) and psychographic (e.g., values, interests) attributes. Each persona independently appraises a stimulus such as an advertisement, video, or webpage, offering both a quantitative score (e.g., click-through likelihood, recall score, likability) and a qualitative rationale. Aggregating these opinions produces a distribution of preferences that more closely mirrors real human crowds. Across eleven behavioral prediction tasks, Social Agents outperforms single-LLM baselines by up to 67.45% on simple judgments (e.g. webpage likability) and 9.88% on complex interpretive reasoning (e.g. video memorability). Social Agents’ individual persona predictions also align with human judgments, reaching Pearson correlations up to 0.71. These results position computational crowd simulation as a scalable, interpretable tool for improving behavioral prediction and supporting societal decision making.
Deep Learning · Theory
Dynamic feature transformation (the rich regime) does not always align with predictive performance (better representation), yet accuracy is often used as a proxy for richness, limiting analysis of their relationship. We propose a computationally efficient, performance-independent metric of richness grounded in the low-rank bias of rich dynamics, which recovers neural collapse as a special case. The metric is empirically more stable than existing alternatives and captures known lazy-to-rich transitions (e.g., grokking) without relying on accuracy. We further use it to examine how training factors (e.g., learning rate) relate to richness, confirming recognized assumptions and highlighting new observations (e.g., batch normalization promote rich dynamics). An eigendecomposition-based visualization is also introduced to support interpretability, together providing a diagnostic tool for studying the relationship between training factors, dynamics, and representations.
Applications · Neuroscience, Cognitive Science
Training recurrent neural networks (RNNs) to perform neuroscience-style tasks has become a popular way to generate hypotheses for how neural circuits in the brain might perform computations. Recent work has demonstrated that task-trained RNNs possess a strong simplicity bias. In particular, this inductive bias often causes RNNs trained on the same task to collapse on effectively the same solution, typically comprised of fixed-point attractors or other low-dimensional dynamical motifs. While such solutions are readily interpretable, this collapse proves counterproductive for the sake of generating a set of genuinely unique hypotheses for how neural computations might be performed. Here we propose Iterative Neural Similarity Deflation (INSD), a simple method to break this inductive bias. By penalizing linear predictivity of neural activity produced by standard task-trained RNNs, we find an alternative class of solutions to classic neuroscience-style RNN tasks. These solutions appear distinct across a battery of analysis techniques, including representational similarity metrics, dynamical systems analysis, and the linear decodability of task-relevant variables. Moreover, these alternative solutions can sometimes achieve superior performance in difficult or out-of-distribution task regimes. Our findings underscore the importance of moving beyond the simplicity bias to uncover richer and more varied models of neural computation.
In observational settings where treatment and outcome are confounded by unobserved factors but an observed mediator satisfies front-door conditions, estimating heterogeneous treatment effects remains underdeveloped. We introduce two debiased learners for heterogeneous front-door effects: FD-DR-Learner and FD-R-Learner. Both methods are constructed to be robust to nuisance estimation error, and we show they achieve fast quasi-oracle rates even when nuisance functions converge as slowly as $n^{-1/4}$. We provide error analyses that clarify their behavior under overlap and nuisance misspecification. In synthetic experiments varying sample size, nuisance noise, and overlap severity, both learners consistently outperform a plug-in baseline, with FD-R showing stronger stability under weak overlap. In a real-world case study using FARS data on primary seat-belt laws, the methods deliver reliable personalized effect estimates and interpretable heterogeneity patterns. Overall, the proposed learners offer practical and sample-efficient tools for heterogeneous causal estimation under front-door identification.
Deep Learning · Theory
Despite the importance of global contextual modeling in visual tasks, a rigorous mathematical definition remains absent, and the concept is still largely described in heuristic or empirical terms. Existing methods either rely on computationally expensive attention mechanisms or are constrained by the recursive modeling nature of State Space Models (SSMs), making it challenging to achieve both efficiency and true global perception. To address this, we first propose a mathematical definition of global modeling for visual images, providing a theoretical foundation for designing globally-aware and interpretable models. Based on in-depth analysis of SSMs and frequency-domain modeling principles, we construct a complete theoretical framework that overcomes the limitations imposed by SSMs' recursive modeling mechanism from a frequency perspective, thereby adapting SSMs for global perception in image modeling. Guided by this framework, we design the Global-aware SSM (GSSM) module and formally prove that it satisfies definitional requirements of global image modeling. GSSM leverages a Discrete Fourier Transform (DFT)-based modulation mechanism, providing precise front-end control over the SSM's modeling behavior, and enabling efficient global image modeling with linear-logarithmic complexity. Building upon GSSM, we develop GMamba, a plug-and-play module that can be seamlessly integrated at any stage of Convolutional Neural Networks (CNNs). Extensive experiments across multiple tasks, including object detection, semantic segmentation, and instance segmentation, across diverse model architectures, demonstrate that GMamba consistently outperforms existing global modeling modules, validating both the effectiveness of our theoretical framework and the rigor of proposed definition. Code is available at \url{https://github.com/Xinmu-Tantai/GMamba-GSSM}