论文检索

Social Aspects · Robustness

Karan Bali, Jack Stanley, Praneet Suresh, Danilo Bzdok

In mechanistic interpretability, recent work scrutinizes transformer “circuits”—sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their stability across different instances of the same deep learning architecture. Without this, it remains unclear whether reported circuits emerge universally across labs or turn out to be idiosyncratic to a particular estimation instance, potentially limiting confidence in safety-critical settings. Here, we systematically study stability across-refits in increasingly complex transformer language models of various sizes. We quantify, layer by layer, how similarly attention heads learn representations across independently initialized training runs. Our rigorous experiments show that (1) middle-layer heads are the least stable yet the most representationally distinct; (2) deeper models exhibit stronger mid-depth divergence; (3) unstable heads in deeper layers become more functionally important than their peers from the same layer; (4) applying weight decay optimization substantially improves attention-head stability across random model initializations; and (5) the residual stream is comparatively stable. Our findings establish the cross-instance robustness of circuits as an essential yet underappreciated prerequisite for scalable oversight, drawing contours around possible white-box monitorability of AI systems.

Deep Learning · Self-Supervised Learning

Zhiyuan Li, Rongzhen Zhao, Wenyan Yang, Wenshuai Zhao, Pekka Marttinen, Joni Pajarinen

The de facto approach in video object-centric learning maintains temporal consistency through learned dynamics modules that predict future object representations, called slots. We demonstrate that these predictors function as expensive approximations of discrete correspondence problems. Modern self-supervised vision backbones already encode instance-discriminative features that distinguish objects reliably. Exploiting these features eliminates the need for learned temporal prediction. We introduce Grounded Correspondence, a framework that replaces learned transition functions with deterministic bipartite matching. Slots initialize from salient regions in frozen backbone features. Frame-to-frame identity is maintained through Hungarian matching on slot representations. The approach requires zero learnable parameters for temporal modeling yet achieves competitive performance on MOVi-D, MOVi-E, and YouTube-VIS. Project page: https://magenta-sherbet-85b101.netlify.app/

Deep Learning · Other Representation Learning

Rongzhen Zhao, Wenyan Yang, Kannala Juho, Joni Pajarinen

Slot Attention (SA) lies at the heart of mainstream Object-Centric Learning (OCL). Image features can be aggregated into object-level representations by SA *iteratively* refining cold-start query slots. For video, such aggregation proceeds by SA *recurrently* shared across frames, with queries cold-started on the first frame while transitioned from the previous frame’s slots thereafter. However, cold-start queries lack sample-specific cues thus hindering precise aggregation on image or video's first frame; Non-first frames' queries are already sample-specific thus requiring aggregation transforms different from the first frame. We address these issues with our *SmoothSA*: (1) To smooth SA iterations on image or video's first frame, we *preheat* cold-start queries with rich input-feature information, by a tiny module self-distilled inside OCL; (2) To smooth SA recurrences across video's first and non-first frames, we *differentiate* the homogeneous aggregation transforms by using full and single iterations respectively. Comprehensive experiments on object discovery, recognition and visual reasoning validate our method's effectiveness. Further visual analyses illuminate the underline mechanisms. Our *source code* and *evaluation log* are provided in the supplement.

Social Aspects · Robustness

Sura Alhanouti, Guzin Bayraksan, Parinaz Naghizadeh

Humans facing algorithmic decision systems have been found to ``game'' them by altering their input data (at a cost to them) in order to favorably change the algorithmic outcomes they receive (at a cost to the algorithm). The growing literature on strategic classification seeks to develop robust machine learning algorithms that account for, and reduce, this strategic behavior. A limitation of these existing works is that they assume the cost of strategic behavior to be fixed and independent of the classifier's decision. In practice, however, manipulation costs evolve and depend on past algorithmic decisions: today's decisions influence tomorrow's costs. This paper proposes and analyzes a two-stage robust optimization framework with a decision-dependent uncertainty set to capture such dependencies. We highlight that awareness of policy-dependent costs not only reduces uncertainty, but also better curtails gaming of the algorithmic system over time.

Social Aspects · Robustness

Kuheli Pratihar, Debdeep Mukhopadhyay

Large language models generate text through probabilistic token sampling, a mechanism increasingly leveraged for inference-time watermarking to verify AI-generated content. We present an information-theoretic framework that characterizes the trade-off between robustness to text editing and detectability by keyless observers, where detectability bounds are information-theoretic and computational attainability depends on detector access. Central to our analysis is an additive, usable Kullback-Leibler (KL) information budget that governs hypothesis testing separability between watermarked and unwatermarked outputs subject to a stealth constraint. This budget induces a hierarchy of detectability across watermark families: distribution-preserving schemes exhibit zero statistical drift, while probability-modifying schemes at both token and sentence levels accumulate detectable signal with sequence length. When text editing is modeled as a noise process, the usable KL budget contracts quadratically with edit rate for token-level schemes and according to an induced semantic flip rate for sentence-level schemes. These contraction laws reveal an irreducible trilemma among robustness, stealth, and reliable verification. Guided by these limits, we propose a hybrid watermarking strategy that selects among distribution-preserving, semantic-level, and token-level methods based on anticipated editing regimes. Experiments on Llama-2-7B and Mistral-7B under paraphrasing attacks corroborate theoretical predictions and confirm that the hybrid strategy is empirically near-Pareto across evaluated edit regimes.

Deep Learning · Generative Models and Autoencoders

Dahee Kwon, Haeun Lee, Jaesik Choi

Recent text-to-image models built on large-scale Transformer backbones and flow-based objectives deliver strong text–image alignment and high visual quality, yet often produce overly similar samples under a fixed prompt. Existing diversity-enhancement methods can increase sample-to-sample variation, but typically rely on extra sampling, auxiliary optimization, or careful tuning—incurring non-trivial runtime and memory overhead. We examine intermediate Transformer features and observe that the lowest-frequency (DC) component rapidly homogenizes across seeds early in generation, infivsyinh an early trajectory lock-in that limits downstream variation. Building on this, we propose DC Attenuation for diVersity Enhancement \textbf{(DAVE)}, a training-free representation-level intervention that selectively attenuates this component in the early regime. DAVE preserves the sampling pipeline and incurs negligible overhead, improving prompt-consistent diversity without sacrificing image quality.

Deep Learning · Generative Models and Autoencoders

Dongyeop Woo, Marta Skreta, Seonghyun Park, Kirill Neklyudov, Sungsoo Ahn

Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to hundreds of neural network evaluations at inference time, which can become a computational bottleneck in large-scale scientific sampling workflows. We introduce Riemannian MeanFlow (RMF), a framework for learning flow maps directly on manifolds, enabling high-quality generations with as few as one forward pass. We derive three equivalent characterizations of the manifold average velocity (Eulerian, Lagrangian, and semigroup identities), and analyze parameterizations and stabilization techniques to improve training on high-dimensional manifolds. In promoter DNA design and protein backbone generation settings, RMF achieves comparable sample quality to prior methods while requiring up to 10$\times$ fewer function evaluations. Finally, we show that few-step flow maps enable efficient reward-guided design through reward look-ahead, where terminal states can be predicted from intermediate steps at minimal additional cost.

Social Aspects · Privacy

Sajani Vithana, Sangwon Jung, Haoyang Hu, Viveck Cadambe, Flavio Calmon, Haewon Jeong

Differential privacy (DP) imposes fundamental trade-offs between privacy and statistical fidelity in synthetic data generation. While access to public data has been shown to improve these trade-offs empirically, existing approaches exploit public data only indirectly, through pre-processing (e.g., using pre-trained generative models) or post-processing steps (e.g., matching target statistics estimated from public datasets), while relying on domain-agnostic DP mechanisms. In this work, we lay the theoretical framework to study the principled incorporation of public data into DP mechanisms themselves. We consider normalized histograms as distribution estimators and characterize the \emph{theoretically optimal} domain-aware privacy mechanism within a class of mixing-based DP mechanisms. We introduce \textsc{PubMix}, a public-data-aware DP mechanism that can be used in histogram-based data synthesis pipelines. Our experiments demonstrate that, when public data is available, \textsc{PubMix} significantly improves synthetic data generation quality across tasks without compromising privacy.

Deep Learning · Large Language Models

Yao Yao, Xinyuan Song, Sebastian Pokutta, Max Zimmer, Nico Pelleriti, Thomas Hofmann, Shiwei Liu

Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance in Pre-Layer Normalization, which can push deep blocks toward near-identity behavior. In this paper, we demonstrate that, sparsity, beyond enabling efficiency, acts as a regulator of variance propagation and thereby improves depth utilization. Our investigation covers two sources of sparsity: (i) implicit sparsity, which emerges from training and data conditions, including weight sparsity induced by weight decay and attention sparsity induced by long-context inputs; and (ii) explicit sparsity, which is enforced by architectural design, including key/value-sharing sparsity in Grouped-Query Attention and expert-activation sparsity in Mixture-of-Experts. Our claim is thoroughly supported by controlled depth-scaling experiments and targeted layer effectiveness interventions. Across settings, we observe a consistent relationship: sparsity improves layer utilization by reducing output variance and promoting functional differentiation. We eventually distill our findings into a practical rule-of-thumb recipe for training depth-effective LLMs, yielding a notable 4.6\% accuracy improvement on downstream tasks. Our results reveal sparsity, arising naturally from standard design choices, as a key yet previously overlooked mechanism for effective depth scaling in LLMs. Code is submitted.

Applications · Computer Vision

Pengfei zhang, Jian Ji

Evaluation metrics establish a standard assessment framework for models, playing a pivotal role in model optimization and advancement. However, widely adopted pixel-wise metrics (e.g., IoU, Dice) rely heavily on pixel-level statistics, often failing to capture the structural integrity of predictions. While the S-measure ($S_m$) incorporates structural perception to some extent, it struggles to differentiate critical structural violations and remains insensitive to background false positives and small objects. To address these limitations, we propose the Topology-aware measure ($T_m$), a novel metric designed to explicitly quantify topological consistency. $T_m$ employs the Fuzzy Jaccard Index as a foundational score, integrates a Topological Integrity term ($I_{topo}$) to penalize critical structural fragmentation, and utilizes a Boundary Alignment term ($\mathcal{A}_{bdy}$) to evaluate boundary alignment. These three components synergize to achieve robust evaluation of prediction maps at the topological level. We establish a rigorous Meta-Measure validation framework and benchmark our method against nine mainstream metrics across diverse complex scenarios. Extensive experiments demonstrate that $T_m$ performs exceptionally in downstream tasks and maintains high consistency with human visual perception.

Deep Learning · Large Language Models

Rosie Zhao, Anshul Shah, Xiaoyu Zhu, Xinke Deng, Zhongyu Jiang, Yang Yang, Joerg Liebelt, Arnab Kumar Mondal

Reinforcement learning (RL) fine-tuning is now widely used to improve LLM reasoning, and recent work has begun extending it to vision-language models (VLMs). While RL-tuned VLMs can improve visual reasoning benchmark performance, they can still suffer from weak visual grounding, hallucinations, and over-reliance on textual cues. We show that simple, controlled textual perturbations—misleading captions or incorrect chain-of-thought (CoT) traces—cause substantial drops in robustness and confidence, and that these effects are more pronounced when CoT consistency is taken into account across open-source multimodal reasoning models. Entropy-based metrics further show that these perturbations reshape model uncertainty on the correct option, exposing model-specific trends in miscalibration. To better understand these vulnerabilities, we further analyze RL fine-tuning dynamics and uncover an accuracy–faithfulness trade-off: fine-tuning raises benchmark accuracy, but can simultaneously erode the reliability of the accompanying CoT and its robustness to contextual shifts. Although adversarial augmentation improves robustness, it does not by itself prevent faithfulness drift. Incorporating a faithfulness-aware reward can restore alignment between answers and reasoning, but when paired with augmentation, training risks collapsing onto shortcut strategies and robustness remains elusive. Together, these findings highlight the limitations of accuracy-only evaluations and motivate training and assessment protocols that jointly emphasize correctness, robustness, and the faithfulness of visually grounded reasoning.

Deep Learning · Large Language Models

Rosie Zhao, Tian Qin, David Alvarez-Melis, Sham Kakade, Naomi Saphra

Language models famously improve under a smooth scaling law, but some specific capabilities exhibit sudden breakthroughs in performance. Advocates of "emergence" view breakthroughs as unlocked capabilities, but others attribute them to metric thresholding effects. We propose that breakthroughs are instead driven by continuous changes in the *probability distribution* of training outcomes when performance is bimodally distributed across random seeds. we show that different random seeds can produce *either* smooth *or* emergent scaling trends in synthetic length generalization tasks, multiple choice question answering, and grammatical generalization. We reveal that sharp breakthroughs in metrics are produced by underlying continuous changes in their distribution across seeds.

Applications · Health / Medicine

Zelin Zang, WenZhe Li, Yongjie Xu, Chang Yu, Changxi Chi, Jingbo Zhou, Zhen Lei, Stan Z Li

In single-cell research, tracing and analyzing high-throughput single-cell differentiation trajectories is crucial for understanding biological processes. Key to this is the robust modeling of hierarchical structures that govern cellular development. Traditional methods face limitations in computational cost, performance, and stability. VAE-based approaches have made strides but still require branch-specific network modules, limiting their scalability and stability, while often suffering from posterior collapse. To overcome these challenges, we introduce HDTree, a generative modeling framework designed for robust lineage inference. HDTree captures tree relationships within a hierarchical latent space using a unified hierarchical codebook and employs a quantized diffusion process to model continuous cell state transitions. By aligning the generative process with the Waddington landscape, this method not only improves stability and scalability but also enhances the biological plausibility of inferred lineages. HDTree's effectiveness is demonstrated through comparisons on both general-purpose and single-cell datasets, where it outperforms existing methods in lineage inference accuracy, reconstruction quality, and hierarchical consistency. These contributions enable accurate and efficient modeling of cellular differentiation paths, offering reliable insights for biological discovery.

General Machine Learning · Transfer, Multitask and Meta-learning

Hanxiao Chen, Debarghya Mukherjee

We study clustered multitask learning in a semiparametric setting where tasks share a latent cluster structure in their target parameters but exhibit heterogeneous, potentially infinite-dimensional nuisance components. Such heterogeneity poses a major challenge for existing multitask learning methods, which typically rely on aligned feature spaces or homogeneous task structures. To address this challenge, we propose an *adaptive fused orthogonal estimator* that integrates Neyman-orthogonal losses with data-driven pairwise fusion penalties. Our framework leverages task-specific pilot estimates to calibrate the fusion penalties and combines adaptive aggregation with orthogonalization to mitigate the impact of nuisance-parameter estimation error. Theoretically, we show that the proposed estimator achieves exact recovery of the latent clustering with high probability and attains pooled parametric convergence rates proportional to cluster size. Moreover, we establish asymptotic normality and show that, asymptotically, our estimator matches the performance of an oracle procedure that knows the true clustering in advance. Empirically, we show that the proposed method consistently outperforms strong baselines in various simulation setups. A real-world application to U.S. residential energy consumption further demonstrates the effectiveness of our approach in uncovering meaningful regional clustering in electricity price elasticity, showcasing the efficacy of our method.

Speed Zhu, Chuheng Zhang, Jianwei Cai, Guang Chen, Lulu Wu, Xiaolong Xu, Xuyun Zhang, Saiyong Yang, Wiggin Zhou

Recent success of large reasoning models (such as OpenAI o1 and DeepSeek R1) have spurred a resurgence of interest in reinforcement learning from verifiable rewards (RLVR). However, progress is still largely driven by RL algorithm design, while data scheduling -- the data-side decisions that determine what the model trains on over time -- is critical but remains underexplored. Therefore, data scheduling becomes the focus of this paper, including how to curate data for supervised fine-tuning (SFT) and how to select prompts and collect rollouts for reinforcement learning (RL). We introduce a pipeline with careful designs on data scheduling, consisting of hardness-prioritized SFT and two-stage RL. Specifically, we first fine-tune the base model on supervision data that is curated to prioritize difficulty based on both arena learning and classification. Then, we introduce two-stage RL where a decreased max sequence length during rollout is used in the first stage to expand entropy and reduce repetition, and a large number rollouts per prompt and curriculum design are adopted in the second stage to encourage exploration for challenging problems. We implement this pipeline on Qwen2.5-32B and an internal 389B MoE model, and evaluate them on a wide range of benchmarks including challenging LeetCode and Codeforces weekly contests. The results not only indicate the effectiveness and scalability of our pipeline but also demonstrate our model achieve sota of 32B models in competitive code generation.

Deep Learning · Large Language Models

Xiang Fang, Wanlong Fang, Wei Ji

Large Vision-Language Models have achieved unprecedented success in zero-shot recognition by aligning visual features with broad semantic concepts. However, this semantic abstraction creates a critical vulnerability in open-world deployment: the "Hubris of Semantics", where models force-fit unknown anomalies into known categories with high confidence due to the lack of explicit negative knowledge. To address this \textit{Open-World Trustworthiness Paradox}, we propose \textbf{Immuno-VLM}, a bio-inspired framework that adapts the biological principle of \textbf{Immunological Negative Selection} to high-dimensional latent spaces. Departing from traditional Open-Set Recognition methods that rely on passive density estimation or inefficient pixel-space outlier generation, Immuno-VLM leverages the generative reasoning of Large Language Models to actively hallucinate ``Semantic Antibodies''—textual descriptions of near-distribution outliers (e.g., look-alikes, contextual anomalies) that effectively bound the decision space of known classes. Extensive experiments on ImageNet-1K and four challenging OOD benchmarks reveal that Immuno-VLM establishes a new state-of-the-art.

Deep Learning · Large Language Models

Xiang Fang, Wanlong Fang

In the era of Large Video-Language Models (LVLMs), the computational necessity of sparse frame sampling creates a fundamental ``temporal gap'', rendering models blind to critical causal transitions. Existing solutions relying on generative hallucination (e.g., latent diffusion) or autoregressive extrapolation often fail to maintain semantic consistency over long horizons, suffering from object vanishing and energetic instability. We propose a paradigm shift from probabilistic generation to variational mechanics with the \textbf{Semantic Least Action Principle (SLAP)}. Drawing a rigorous isomorphism between classical mechanics and semantic dynamics, we model the latent video trajectory as a path on a Riemannian manifold governed by a Semantic Lagrangian. By formulating the interpolation task as a Boundary Value Problem (BVP) solved via the discrete Euler-Lagrange equations, SLAP naturally enforces object persistence without pixel-level rendering. Extensive experiments on multiple challenging datasets show the effectiveness of our proposed SLAP.

Social Aspects · Alignment

Gaojie Jin, Yong Tao, Lijia Yu, Tianjin Huang

Jung et al. (2025) introduce a hypothesis testing framework for guaranteeing agreement between large language models (LLMs) and human judgments, relying on the assumption that the model’s estimated confidence is monotonic with respect to human-disagreement risk. In practice, however, this assumption may be violated, and the generalization behavior of the confidence estimator is not explicitly analyzed. We mitigate these issues by learning a dedicated confidence estimator instead of relying on heuristic confidence signals. Our approach leverages simulated annotator diversity and a margin-based ranking formulation to explicitly model how confidently an LLM distinguishes between human-agreement and human-disagreement cases. We further derive generalization guarantees for this estimator, revealing a margin-dependent trade-off that informs the design of an adaptive estimator training procedure. When integrated into fixed-sequence testing, the learned confidence estimator yields improved ranking accuracy and empirically strengthens the monotonic relationship between confidence and disagreement risk, leading to higher success rates in satisfying target agreement levels across multiple datasets and judge models.

Applications · Computer Vision

Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen, Ke-Yue Zhang, Yue Zhou, Caiyong Piao, Bin Li, Taiping Yao, Bo Wang, Youchang xiao 等

Multimodal large language models (MLLMs) have been increasingly adopted in forensics for their robust semantic understanding. As AI-generated images become realistic, semantic-level inconsistencies alone are often insufficient for reliable detection. This motivates a critical question: *whether MLLMs can achieve full-spectrum forensic signal perception, i.e., capturing low-level generator artifacts without sacrificing pre-trained semantic knowledge.* We then conduct a layer-wise analysis of forensic signal perception in MLLMs and find that semantic information is mainly encoded in the early-to-middle layers, and directly fine-tuning MLLMs for artifact learning causes rapid semantic forgetting. Based on this insight, we propose Deep Visual Residual MLLM (Deep-VRM) to \textit{preserve early semantic processing while injecting artifact-specific visual signals as a residual path into an intermediate layer}, where they are fused with semantic token representations and propagated through subsequent trainable layers. This enables later layers to jointly model semantic reasoning and signal-level forensic cues, and surprisingly, the model learns to adaptively leverage different levels of forensic signals depending on the input, achieving robust and generalizable detection performance. Extensive experiments show that our method achieves state-of-the-art across all benchmarks.

Deep Learning · Large Language Models

Liulu He, Xuan Ang Liu, Juntao Liu, Taolue Feng, Ting Lu, Chunsheng Gan, ZHIYV PENG, Yuan Du, Li Du, Huanrui Yang 等

Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), creating a "deployment gap" where LLMs cannot be optimally fitted to specific memory budgets. To bridge this gap, we introduce LiftQuant, a novel framework that enables continuous bit-width control for true Pareto-optimal deployment. The core innovation is a "lift-then-project" mechanism: we represent d-dimensional weight vectors by projecting a simple 1-bit lattice from a tunable D-dimensional "lifted" space. By adjusting the lifted dimension D, LiftQuant naturally yields an effective bit-width of D/d, allowing for seamless, continuous resolution adjustment rather than discrete steps. This projection generates a structured yet non-uniform codebook, capturing the expressive power of Vector Quantization. Crucially, its decoding path relies solely on linear transformations and 1-bit uniform quantizers, retaining hardware-friendly efficiency. This flexibility is transformative: LiftQuant enables a 70B LLM to be compressed to 2.4 bits to precisely fit a 24GB GPU, where its performance significantly surpasses state-of-the-art 2-bit models. With a decoding throughput up to 6.7x faster than FP16, LiftQuant redefines compression as a continuous optimization problem, paving the way for a new generation of hardware-aware LLM deployment.