论文检索

Deep Learning · Large Language Models

Meimingwei Li, Yuanhao Ding, Esteban Garces Arias, Christian Heumann

Recent work has identified a counterintuitive phenomenon termed “Hyperfitting", where fine-tuning Large Language Models (LLMs) to near-zero training loss on small datasets surprisingly enhances open-ended generation quality and mitigates repetition in greedy decoding. While effective, the underlying mechanism remains poorly understood, with the extremely low-entropy output distributions suggesting a potential equivalence to simple temperature scaling. In this work, we demonstrate that this phenomenon is fundamentally distinct from distribution sharpening; entropy-matched control experiments reveal that temperature scaling fails to replicate the diversity gains of hyperfitting. Furthermore, we falsify the hypothesis of static vocabulary reweighting, showing through ablation studies that hyperfitting relies on a dynamic, context-dependent rank reordering mechanism. Layer-wise analysis localizes this effect to a “Terminal Expansion" in the final transformer block, where a substantial geometric expansion of the feature space ($\Delta \mathrm{Dim} \approx +80.8$) facilitates the promotion of deep-tail tokens. And we introduce \textbf{Late-Stage LoRA}, a targeted fine-tuning strategy that updates only the final 5 layers, achieving robust generation with minimal parameter updates.

Deep Learning · Large Language Models

Zishan Shao, Lixun Zhang, Kangning Cui, Yixiao Wang, Ting Jiang, Hancheng Ye, Qinsi Wang, Zhixu Du, Yuzhe Fu, Fan Yang 等

Large language models (LLMs) handle many tasks with one set of parameters, but under KV-cached inference it is unclear what task-general structure, if any, is used at $\textit{decode time}$ rather than during $\textit{prefill}$. We propose $\textbf{DecodeShare}$, a protocol that identifies a low-dimensional subspace that is consistently shared across tasks in decode-time hidden states, and then tests its causal role by removing that subspace only during decoding. In our experiments, disturbing the discovered shared subspace degrades decision performance far more than disturbing either a prefill-derived subspace or a random subspace under the same intervention budget. We further find that this decode-shared subspace overlaps common steering vectors, enabling a simple offline adjustment: projecting steering vectors away from the shared subspace can reduce template sensitivity while preserving non-random task utility, with task-dependent trade-offs. Despite being compact, the shared subspace can serve as a high-leverage causal channel at decode time.

General Machine Learning · Evaluation

Michael Hardy, Sang Truong, Anka Reuel, Lijin Zhang, Jodi Casabianca, Yash Dave, Hansol Lee, Ben Domingue, Sanmi Koyejo

AI benchmark ecosystems compress rich evaluation data into aggregate leaderboard scores, but these scores contain substantial measurement noise whose sources and magnitudes remain unquantified. Without systematic methods to measure this noise and separate signal from artifact, it is unclear when benchmark rankings reflect genuine capability differences versus measurement error. We introduce a psychometric framework to methodically test hypotheses about benchmark ecosystem structure and quantify the reliability of common benchmark-derived claims. Applying Confirmatory Factor Analysis and Generalizability Theory to 4,000+ models from the Open LLM Leaderboard, we decompose sources of ranking variance and find that human contributors account for more variance (9\%) than model architecture (4.8\%), revealing that benchmark noise stems as much from contributor practices as from model characteristics. We further demonstrate methods to assess the reliability of scaling laws by controlling for model size and other confounds. Our findings provide actionable diagnostics for when benchmark rankings can be trusted and establish a measurement framework for evaluating the validity of AI evaluation claims.

Deep Learning · Large Language Models

Tong Wu, Michael Liu, Jun Bai, Zixia Jia, Shuyi Zhang, Ziyong Lin, Yanting Wang, Song-Chun Zhu, Zilong Zheng

We introduce **Native Parallel Reasoner (NPR)**, a teacher-free framework that enables Large Language Models (LLMs) to self-evolve genuine parallel reasoning capabilities. NPR transforms the model from sequential emulation to native parallel cognition through three key innovations: 1) a **self-distilled** progressive training paradigm that transitions from ``cold-start'' format discovery to strict topological constraints without external supervision; 2) a novel **Parallel-Aware Policy Optimization (PAPO)** algorithm that optimizes branching policies directly within the execution graph, allowing the model to learn adaptive decomposition via trial and error; and 3) a robust **NPR Engine** that refactors memory management and flow control of SGLang to enable stable, large-scale parallel RL training. Across eight reasoning benchmarks, NPR trained on Qwen3-4B achieves performance gains of up to 24.5\% and inference speedups up to 4.6$\times$. Unlike prior baselines that often fall back to autoregressive decoding, NPR demonstrates 100\% genuine parallel execution, establishing a new standard for self-evolving, efficient, and scalable agentic reasoning.

Deep Learning · Large Language Models

Sina Mansouri, Mohit Marvania, Abolfazl Safikhani

The widespread adoption of large language models (LLMs) has intensified the demand for principled methods to distinguish human- from machine-generated text. Watermarking provides a promising avenue, yet existing detectors exhibit sharp performance deterioration under multiple paraphrasing and when applied to shorter texts. We introduce Pattern Stability Score (PSS), a novel detection framework that leverages local statistical features and stability dynamics across paraphrased variants. Specifically, the proposed method combines global and local z-score features with higher-order statistics of run-length patterns, enriched by autocorrelation signals and stability scores computed over paraphrase depth. Numerical evaluations are performed on three benchmark datasets (PG-19, CNN/DailyMail, and WikiText) using multiple LLMs (Llama-3-8B, Qwen2-7B) and paraphrasers (Mistral-7B, Qwen2-7B, Gemma-7B), systematically stress-testing robustness under up to eight rounds of paraphrasing. Compared to prior z-score thresholding baselines and some state-of-the-art deep learning methods, our approach improves detection AUC (area under the receiver operating characteristic curve) by over 10-15 percentage points across different token lengths. Additionally, extensive cross-domain experiments demonstrate that a single universal classifier generalizes across different LLMs, paraphrasers, and text domains without retraining, maintaining above 83.7\% AUC even when all components differ from training.

Deep Learning · Foundation Models

Yichen Gong, Zhuohan Cai, Sunhao Dai, Yuqi Zhou, Zhangxuan Gu, Changhua Meng, Shuheng Shen

Existing online benchmarks for mobile GUI agents remain largely app-centric and task-homogeneous, failing to reflect the diversity and instability of real-world mobile usage. To this end, we introduce VenusBench-Mobile, a challenging online benchmark for evaluating general-purpose mobile GUI agents under realistic, user-centric conditions. VenusBench-Mobile builds two core evaluation pillars: defining what to evaluate via user-intent-driven task design that reflects real mobile usage, and how to evaluate through a capability-oriented annotation scheme for fine-grained agent behavior analysis. Extensive evaluation of state-of-the-art mobile GUI agents reveals large performance gaps relative to prior benchmarks, indicating that VenusBench-Mobile poses substantially more challenging and realistic tasks and that current agents remain far from reliable real-world deployment. Diagnostic analysis further shows that failures are dominated by deficiencies in perception and memory, which are largely obscured by coarse-grained evaluations. Moreover, even the strongest agents exhibit near-zero success under environment variations, highlighting their brittleness in realistic settings. Based on these insights, we believe VenusBench-Mobile provides an important stepping stone toward robust real-world deployment of mobile GUI agents.

Deep Learning · Theory

Muhammad Ashiq, Samanyu Arora, Abhinav Narayan Harish, Ishaan Kharbanda, Hung Yun Tseng, Grigorios Chrysos

We theoretically study the hallucination phenomena in two canonical diffusion samplers: the stochastic Denoising Diffusion Probabilistic Model (DDPM) and the deterministic Denoising Diffusion Implicit Model (DDIM). We analyze the reverse ODE (DDIM) and SDE (DDPM) for a Gaussian mixture target, proving that after a critical time $\tau$, (a) DDIM can become stuck on the segment connecting the two nearest modes and (b) the *stochasticity of DDPM* helps DDPM become unstuck from this region, thus avoiding hallucination. Our empirical validation verifies that DDPM has a significantly lower hallucination rate than DDIM when this region is entered. Building on our observations, we exhibit how using additional stochastic steps can help DDIM avoid hallucinations and offer new insights on how to design improved samplers.

Theory · Probabilistic Methods

Deming Sheng, Ricardo Henao

Modern neural classifiers can achieve remarkable predictive performance, yet often suffer from *miscalibration*. In this paper, we introduce a unified calibration framework applicable to arbitrary distribution-based classifiers. The proposed calibration objective guarantees a *monotone Probably Approximately Individually Calibrated (mPAIC)* predictor, which theoretically implies the properties of a *Probably Approximately Calibrated Classifier (PACC)* with explicit error bounds. To enable stable and effective optimization, we further devise a *Decoupled Dual-Stream Optimization (DDSO)* strategy with gradient detachment to reconcile discriminative representation learning and continuous calibration. Notably, our framework bridges calibration paradigms, supporting flexible deployment either as an end-to-end *pre-calibration* objective or as a lightweight *post-calibration* adapter. Extensive experiments across nine real-world datasets demonstrate that our approach consistently outperforms strong baselines, achieving superior performance on both *accuracy* and multi-level *calibration*.

Deep Learning · Everything Else

Meng Bi, Hong Huang, Jinlong Song, Charles Wang, Chengming Hu, Xi Chen, Ting Yu, Xue Liu

Cross-device Federated Learning (FL) is frequently bottlenecked by the prohibitive computational and communication costs of training deep neural networks on resource-constrained edge hardware. While federated dynamic pruning aims to alleviate these costs by adjusting sparse topologies during training, existing methods rely on magnitude-based heuristics that are fundamentally ill-suited for the non-convergent, heterogeneous environments inherent to FL. To address this challenge, we propose Fedfit, a federated dynamic framework that replaces simple heuristics with optimization-centric criteria for topology adjustment. By leveraging a second-order approximation of the loss landscape via the Fisher Information Matrix, Fedfit enables precise and efficient topology adjustment without the overhead of explicit Hessian computation. Empirical evaluations across computer vision and natural language processing benchmarks demonstrate that Fedfit significantly narrows the sparse-to-dense accuracy gap, outperforming state-of-the-art methods while maintaining high communication efficiency.

Applications · Health / Medicine

Jian Chen, Yipeng Du, Wenhao Yuan, Shuai Wang, Jinfeng Xu, Zewei Liu, Running Zhao, Edith Ngai

Electrocardiogram (ECG) representation learning via ECG-report alignment is often hindered by the inherent structural and statistical divergence between signals and natural language. Existing methods struggle to bridge this gap with simple contrastive objectives, but struggle with distribution dependencies between heterogeneous features. To address this, we propose **SGERA** (**S**tein-**G**uided **E**CG-**R**eport **A**lignment), which leverages the unique properties of Stein kernels to provide a more rigorous geometric alignment in the latent space: **instance-level** alignment via a Stein-RBF kernel enforces pairwise consistency between ECG and report embeddings and **distribution-level** alignment via a Stein-Score kernel captures higher-order interactions for global alignment. Furthermore, we introduce an ECG-Report matching task with a Hard Sample Mining strategy to refine discriminative boundaries. Experiments across three public datasets demonstrate that SGERA significantly outperforms state-of-the-art SSL methods in zero-shot classification, linear probing, and transfer learning, proving the superiority of Stein-guided alignment in handling complex medical modalities. Code is available at supplementary materials.

Applications · Computer Vision

Nickolay Safonov, Dmitriy Vatolin

Video quality assessment (VQA) plays a critical role in optimizing video delivery systems. While numerous objective metrics have been proposed to approximate human perception, the perceived quality strongly depends on viewing conditions and display characteristics. Factors such as ambient lighting, display brightness, and resolution significantly influence the visibility of distortions. In this work, we address the question of the multi-screen quality assessment on mobile devices, as this area still tends to be under-covered. We introduce a first large-scale subjective dataset collected across more than different 300 Android devices, accompanied by metadata on viewing conditions and display properties. We propose a strategy for aggregated score extraction and adaptation of VQA models to device-specific quality estimation. Our results demonstrate that incorporating device and context information enables more accurate and flexible quality prediction, offering new opportunities for fine-grained optimization in streaming services. Ultimately, this work advances the development of perceptual quality models that bridge the gap between laboratory evaluations and the diverse conditions of real-world media consumption. We made the dataset and the code available at [Link is redacted].

Applications · Chemistry, Physics, and Earth Sciences

Daria Ledneva, Mikhail Nuridinov, Denis Kuznetsov

Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reporting. As a result, claims of superiority or generality across models are often not directly comparable. We introduce GENEB, a large-scale diagnostic benchmark that evaluates frozen representations from 40 genomic foundation models across 100 tasks spanning 13 functional categories under a unified probing-based protocol, including few-shot regimes. GENEB enables controlled comparison across model scale, architecture, tokenization, and pretraining data while explicitly exposing task-level trade-offs. Our analysis shows that aggregate leaderboards are unstable: model rankings vary sharply across task categories, scale provides only modest and inconsistent gains, and architectural and pretraining alignment frequently outweigh parameter count. These results highlight limitations of current evaluation practices and position GENEB as a reference framework for principled comparison and category-aware model selection in genomic machine learning.

Theory · Online Learning and Bandits

Lorenzo Croissant

Linear bandits have long been a central topic in online learning, with applications ranging from recommendation systems to adaptive clinical trials. Their general learnability has been established when the objective is to minimise the inner product between a cost parameter and the decision variable. While this is highly general, this reliance on an inner product structure belies the name of \emph{linear} bandits, and fails to account for problems such as Optimal Transport. Using the Kantorovich formulation of Optimal Transport as an example, this article shows that an inner product structure is \emph{not} necessary to achieve efficient learning in linear bandits. We propose a refinement of the classical OFUL algorithm that operates by embedding the action set into a Hilbertian subspace, where confidence sets can be built via least-squares estimation. Actions are then constrained to this subspace by penalising optimism. The analysis is completed by leveraging convergence results from penalised (entropic) transport to the Kantorovich problem. Up to this approximation term, the resulting algorithm achieves the same trajectorial regret upper bounds as the OFUL algorithm, which we turn into worst-case regret using functional regression techniques. Its regret interpolates between $\tilde{\mathcal O}(\sqrt{T})$ and ${\mathcal O}(T)$, depending on the regularity of the cost function, and recovers the parametric rate $\tilde{\mathcal O}(\sqrt{dT})$ in finite-dimensional settings.

Applications · Computer Vision

Aleksandr Gushchin, Dmitriy Vatolin, Anastasia Antsiferova

Full-Reference image quality assessment (FR IQA) is important for image compression, restoration and generative modeling, yet current neural metrics remain slow and vulnerable to adversarial perturbations. We present BiRQA, a compact FR IQA metric model that processes four fast complementary features within a bidirectional multiscale pyramid. A bottom-up attention module injects fine-scale cues into coarse levels through an uncertainty-aware gate, while a top-down cross-gating block routes semantic context back to high resolution. To enhance robustness, we introduce Anchored Adversarial Training, a theoretically grounded strategy that uses clean "anchor" samples and a ranking loss to bound pointwise prediction error under attacks. On five public FR IQA benchmarks BiRQA outperforms or matches the previous state of the art (SOTA) while running $\sim 3 \times$ faster than previous SOTA models. Under unseen white-box attacks it lifts SROCC from 0.30-0.57 to 0.60-0.84 on KADID-10k, demonstrating substantial robustness gains. To our knowledge, BiRQA is the only FR IQA model combining competitive accuracy with real-time throughput and strong adversarial resilience.

Applications · Health / Medicine

Zaifei YANG, Samuel Choi, James Kwok

Protein-protein interactions (PPIs) are essential for a wide range of biological processes. However, existing PPI prediction approaches still face two major limitations. First, in aggregating residue features into global protein features, they ignore the hierarchical organization of proteins, in which meso-scale motifs are the key regulators of PPIs. Second, despite the availability of complementary information across the sequence, structure, and function modalities, current PPI methods fail to integrate all three modalities effectively. To address these limitations, we propose a Hierarchical Motif-based M ultiM odal protein Encoder for PPI Prediction (MMM-PPI), which constructs protein embeddings for PPI prediction in a bottom-up, multi-modal manner. (i) At the micro-scale, we encode three modal residue features; (ii) At the meso-scale, we use a novel multimodal motif encoder to aggregate residues into spatially-informed motif embeddings; (iii) At the macro-scale, we introduce a multimodal protein encoder to integrate motif embeddings into protein embeddings, considering both the relative importance of motifs in PPI and correlations between different modalities. The pre-trained encoder can be used off-the-shelf for large-scale PPI prediction. Extensive experiments on multiple PPI datasets demonstrate that MMM-PPI outperforms state-of-the-art multi-label PPI prediction models, particularly in scenarios with challenging data partitions and limited training data.

General Machine Learning · Representation Learning

Wenxiang Diao, Lei Wang, Andrew Busch, Jun Zhou, Yongsheng Gao

Video anomaly detection (VAD) is critical for surveillance systems, but current methods prioritize accuracy while ignoring the ethical risks of encoding sensitive biometric information. This neglect poses significant privacy concerns for real-world deployment. To bridge this gap, we introduce the Guided Orthogonal Projection Layer (G-OPL), a lightweight module designed to geometrically decouple and suppress sensitive attributes from latent features to produce representations focused on anomaly-relevant cues. We specifically target facial information as the primary sensitive attribute. Unlike gait or body pose, faces act as unique biometric identifiers that are tightly regulated and pose immediate risks of misuse, yet are rarely necessary for identifying abnormal behaviors. To achieve this, G-OPL utilizes a stable, QR-decomposition-based orthogonal projection mechanism guided by weak supervision (e.g., face presence) to actively filter privacy-sensitive subspaces while preserving task-relevant anomalies. we further propose a novel privacy-aware evaluation framework to rigorously quantify the trade-off between model utility and ethical alignment. Our analysis uncovers how projection layers filter sensitive information, why this improves transparency, and under what conditions ethical design also enhances robustness. Extensive experiments demonstrate that our approach effectively minimizes privacy risks without compromising anomaly detection performance, offering a principled path toward trustworthy video analysis.

Probabilistic Methods · Monte Carlo and Sampling Methods

Felix Petersen, Christian Borgelt, Aashwin Mishra, Stefano Ermon

We address the problem of gradient estimation for stochastic differentiable relaxations of algorithms, operators, simulators, and other non-differentiable functions. Stochastic smoothing conventionally perturbs the input of a non-differentiable function with a differentiable density distribution with full support, smoothing it and enabling gradient estimation. Our theory starts at first principles to derive stochastic smoothing with reduced assumptions, without requiring a differentiable density nor full support, and presenting a general framework for relaxation and gradient estimation of non-differentiable black-box functions . We develop variance reduction for gradient estimation from 3 orthogonal perspectives. Empirically, we benchmark 6 distributions and up to 24 variance reduction strategies for differentiable sorting and ranking, differentiable shortest-paths on graphs, differentiable rendering for pose estimation, as well as differentiable cryo-electron tomography simulations.

Applications · Health / Medicine

Jiarui Jin, Haoyu Wang, Xingliang Wu, Xiaocheng Fang, Xiang Lan, Zihan Wang, Deyun Zhang, Bo Liu, Yingying Zhang, Xian Wu 等

Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using \textit{Protocol-Guided Instruction Data Generation}, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with \textit{Interleaved Modality Dropout} to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we propose \textit{Reinforcement Learning with ECG Diagnostic Evidence Rewards} to explicitly supervise diagnostic evidence and strengthen reasoning quality. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are pervasive in these MLLMs, suggesting that their outputs should not be relied upon by the public. Code will be released upon acceptance.

General Machine Learning · Representation Learning

Hahyeon Choi, NOJUN KWAK

We propose S3 (Specialization, Selection, Sparsification), a framework that rethinks multimodal learning through a structural perspective. Instead of encoding all signals into a fixed embedding, S3 decomposes multimodal inputs into semantic experts and selectively routes them for each task. Specialization forms concept-level experts in a shared latent space, Selection adapts routing for task-specific needs, and Sparsification prunes low-utility paths to yield compact, information-minimal representations. Across four MultiBench benchmarks, S3 improves accuracy and exhibits consistent sparsity-performance dynamics, exhibiting a reverse U-shaped trend, with performance peaking at intermediate sparsity. These results suggest that structuring multimodal representations as selectable semantic components provides a practical and principled alternative to contrastive learning or InfoMax-driven approaches.

Applications · Time Series

Ji-Eun Choi, Jae-Hong Lee, Joon Hyuk Chang

Multivariate time-series forecasting (MTSF) learns from high-dimensional covariates with strong temporal dependence, periodic structure, and cross-variable correlations. While modern pipelines often mitigate non-stationarity through instance-wise normalization and decomposition, these interventions operate at the data level and do not directly control dependence that can emerge among the parameters during training. We study MTSF optimization from a parameter-decorrelation viewpoint. Modeling stochastic optimization as a Markov chain in parameter space and leveraging its stochastic differential equation interpretation, we use the per-step transition-variance induced by gradient noise as a tractable signal for optimization-induced dependence and update uncertainty. This signal can empirically inflate during training; we theoretically show that such inflation can degrade generalization diagnostics. Motivated by this mechanism, we propose transition-variance alignment (TVA), an architecture-agnostic procedure that regulates transition-variance by smoothly gating the step size based on the mismatch between an estimated noise scale and a chosen target. TVA maintains effective transition-variance near a prescribed scale without architectural changes, incurs negligible overhead, and integrates seamlessly with diverse methods. Across real-world multivariate benchmarks, TVA consistently improves forecasting accuracy.