论文检索

Reinforcement Learning · Everything Else

Chaorui Yao, Yanxi Chen, Yuchang Sun, Yushuo Chen, Wenhao Zhang, Xuchen Pan, Yaliang Li, Bolin Ding

Off-policy reinforcement learning (RL) for large language models (LLMs) is attracting growing interest, driven by practical constraints in real-world applications, the complexity of LLM-RL infrastructure, and the need for further innovations of RL methodologies. While classic REINFORCE and its modern variants like Group Relative Policy Optimization (GRPO) are typically regarded as on-policy algorithms with limited tolerance of off-policyness, we present in this work a first-principles derivation for group-relative REINFORCE — a REINFORCE variant that uses the within-group mean reward as the baseline for advantage calculation — without assuming a specific training data distribution, showing that it admits a native off-policy interpretation. This perspective yields two general principles for adapting REINFORCE to truly off-policy settings: regularizing policy updates, and actively shaping the data distribution. Our analysis demystifies some myths about the roles of importance sampling and clipping in GRPO, unifies and reinterprets two recent algorithms — Online Policy Mirror Descent and Asymmetric REINFORCE — as regularized forms of the REINFORCE loss, and offers theoretical justification for seemingly heuristic data-weighting strategies. Our findings lead to actionable insights that are validated with extensive empirical studies, and open up new opportunities for principled algorithm design in off-policy RL for LLMs. Source code for this work is available at https://github.com/agentscope-ai/Trinity-RFT/tree/main/examples/rec_gsm8k.

Theory · Interpretability and Visualization

Vishal Pramanik, Maisha Maliha, Nathaniel Bastian, Sumit Jha

Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear approximations that fail to capture the causal and semantic complexities of autoregressive generation in decoder-only models. To address these limitations, we propose **Hessian-Enhanced Token Attribution (HETA)**, a novel attribution framework tailored for decoder-only language models. HETA combines three complementary components: a semantic transition vector that captures token-to-token influence across layers, Hessian-based sensitivity scores that model second-order effects, and KL divergence to measure information loss when tokens are masked. This unified design produces context-aware, causally faithful, and semantically grounded attributions. Additionally, we introduce a **curated benchmark dataset** for systematically evaluating attribution quality in generative settings. Empirical evaluations across multiple models and datasets demonstrate that HETA consistently outperforms existing methods in attribution faithfulness and alignment with human annotations, establishing a new standard for interpretability in autoregressive language models.

Computer Vision · Everything Else

Zimin Xia, Chenghao Xu, Alexandre Alahi

We propose an accurate and interpretable fine-grained cross-view localization method that estimates the 3 Degrees of Freedom (DoF) pose of a ground-level image by matching its local features with a reference aerial image. Unlike prior approaches that rely on global descriptors or bird’s-eye-view (BEV) transformations, our method directly learns ground–aerial image-plane correspondences using weak supervision from camera poses. The matched ground points are lifted into BEV space with monocular depth predictions, and scale-aware Procrustes alignment is then applied to estimate camera rotation, translation, and optionally the scale between relative depth and the aerial metric space. This formulation is lightweight, end-to-end trainable, and requires no pixel-level annotations. Experiments show state-of-the-art accuracy in challenging scenarios such as cross-area testing and unknown orientation. Furthermore, our method offers strong interpretability: correspondence quality directly reflects localization accuracy and enables outlier rejection via RANSAC, while overlaying the re-scaled ground layout on the aerial image provides an intuitive visual cue of localization performance.

General Machine Learning · Representation Learning

Wendi Ren, Ke Wan, Junyu Leng, Shuang Li

One of the central challenges in artificial intelligence is reasoning under partial observability, where key values are missing but essential for understanding and modeling the system. This paper presents a neuro-symbolic framework for latent rule discovery and missing value imputation. In contrast to traditional latent variable models, our approach treats missing grounded values as latent predicates to be inferred through logical reasoning. By interleaving neural representation learning with symbolic rule induction, the model iteratively discovers—both conjunctive and disjunctive rules—that explain observed patterns and recover missing entries. Our framework seamlessly handles heterogeneous data, reasoning over both discrete and continuous features by learning soft predicates from continuous values. Crucially, the inferred values not only fill in gaps in the data but also serve as supporting evidence for further rule induction and inference—creating a feedback loop in which imputation and rule mining reinforce one another. Using a staged block-coordinate gradient descent, the system learns these rules end-to-end by iteratively optimizing over parameter blocks in an alternating fashion. Experiments on both synthetic and real-world datasets demonstrate that our method effectively imputes missing values while uncovering meaningful, human-interpretable rules that govern system dynamics.

Theory · Interpretability and Visualization

Javier Sanguino Bautiste, Thomas Kehrenberg, Carlos Rosety, Jose A. Lozano, Novi Quadrianto

Performative Prediction studies settings where deploying a model induces a distribution shift in the data with the aim of building robust and good-peforming models under these post-deployment effects. Most existing work in this area is theoretical and relies on strict assumptions to converge to those models, which makes the resulting techniques difficult to apply in practice and limits their accessibility to the broader Machine Learning (ML) community. In this blog post, we use visualization techniques 1) to provide an intuitive explanation of Performative Prediction and 2) to extract practical insights for studying convergence when theoretical assumptions do not hold.

Social Aspects · Fairness, Equity, Justice and Safety

Jianwei Li, Jung-Eun Kim

As large language models (LLMs) are overwhelmingly more and more integrated into various applications, ensuring they generate safe responses is a pressing need. Previous studies on alignment have largely focused on general instruction-following but have often overlooked the distinct properties of safety alignment, such as the brittleness of safety mechanisms. To bridge the gap, we propose the Superficial Safety Alignment Hypothesis (SSAH), which posits that safety alignment teaches an otherwise unsafe model to choose the correct reasoning direction - fulfill or refuse users' requests - interpreted as an implicit binary classification task. Through SSAH, we hypothesize that only a few essential components can establish safety guardrails in LLMs. We successfully identify four types of attribute-critical components: Safety Critical Unit (SCU), Utility Critical Unit (UCU), Complex Unit (CU), and Redundant Unit (RU). Our findings show that freezing certain safety-critical components during fine-tuning allows the model to retain its safety attributes while adapting to new tasks. Similarly, we show that leveraging redundant units in the pre-trained model as an "alignment budget" can effectively minimize the alignment tax while achieving the alignment goal. All considered, this paper concludes that the atomic functional unit for safety in LLMs is at the neuron level and underscores that safety alignment should not be complicated.

Applications · Genetics, Cell Biology, Health, etc

Heming Zhang, Di Huang, Wenyu Li, Michael Province, Yixin Chen, Philip Payne, Fuhai Li

In precision medicine, quantitative multi-omic features, topological context, and textual biological knowledge play vital roles in identifying disease-critical signaling pathways and targets, guiding the discovery of novel therapeutics and effective treatment strategies. Existing pipelines capture only one or two of these—numerical omics ignore topological context, text-centric LLMs lack quantitative grounded reasoning, and graph-only models underuse rich node semantics and the generalization power of LLMs—thereby limiting mechanistic interpretability. Although Process Reward Models (PRMs) aim to guide reasoning in LLMs, they remain limited by coarse step definitions, unreliable intermediate evaluation, and vulnerability to reward hacking with added computational cost. These gaps motivate jointly integrating quantitative multi-omic signals, topological structure with node annotations, and literature-scale text via LLMs, using subgraph reasoning as the principle bridge linking numeric evidence, topological knowledge and language context. To resolve this challenge, we propose GALAX (Graph Augmented LAnguage model with eXplainability), an innovative framework that integrates pretrained Graph Neural Networks (GNNs) into Large Language Models (LLMs) via reinforcement learning guided by a Graph Process Reward Model (GPRM), which generates disease-relevant subgraphs in a step-wise manner initiated by an LLM and iteratively evaluated by a pretrained GNN and schema-based rule check, enabling process-level supervision without explicit labels. As an application, we also introduced Target-QA, a benchmark combining CRISPR-identified targets, multi-omic profiles, and biomedical graph knowledge across diverse cancer cell lines, which enables GNN pretraining for supervising step-wise graph construction and supports long-context reasoning over text-numeric graphs (TNGs), providing a scalable and biologically grounded framework for explainable, reinforcement-guided subgraph reasoning toward reliable and interpretable target and pathway discovery in precision medicine.

Applications · Robotics

Xiaolou Sun, Wufei Si, Wenhui Ni, Yuntian Li, Dongming Wu, Fei Xie, Runwei Guan, He-Yang Xu, Henghui Ding, Yuan Wu 等

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes. However, real-world outdoor exploration typically occurs in unknown environments where detailed navigation instructions are unavailable. Instead, only coarse-grained positional or directional guidance can be provided, requiring UAVs to autonomously navigate through continuous planning and obstacle avoidance. To bridge this gap, we propose AutoFly, an end-to-end Vision-Language-Action (VLA) model for autonomous UAV navigation. AutoFly incorporates a pseudo-depth encoder that derives depth-aware features from RGB inputs to enhance spatial reasoning, coupled with a progressive two-stage training strategy that effectively aligns visual, depth, and linguistic representations with action policies. Moreover, existing VLN datasets have fundamental limitations for real-world autonomous navigation, stemming from their heavy reliance on explicit instruction-following over autonomous decision-making and insufficient real-world data. To address these issues, we construct a novel autonomous navigation dataset that shifts the paradigm from instruction-following to autonomous behavior modeling through: (1) trajectory collection emphasizing continuous obstacle avoidance, autonomous planning, and recognition workflows; (2) comprehensive real-world data integration. Experimental results demonstrate that AutoFly achieves a 3.9\% higher success rate compared to state-of-the-art VLA baselines, with consistent performance across simulated and real environments.

Deep Learning · Algorithms

Runjia Zeng, Qifan Wang, Qiang Guan, Ruixiang Tang, Lifu Huang, Zhenting Wang, Xueling Zhang, Cheng Han, Dongfang Liu

Fine tuning has been regarded as a de facto approach for adapting large language models (LLMs) to downstream tasks, but the high training memory consumption inherited from LLMs makes this process inefficient. Among existing memory efficient approaches, activation-related optimization has proven particularly effective, as activations consistently dominate overall memory consumption. Although prior arts offer various activation optimization strategies, their data-agnostic nature ultimately results in ineffective and unstable fine tuning. In this paper, we propose TokenSeek, a universal plugin solution for various transformer-based models through instance-aware token seeking and ditching, achieving significant fine-tuning memory savings (e.g., requiring only 14.8% of the memory on Llama3.2 1B) with on-par or even better performance. Furthermore, our interpretable token seeking process reveals the underlying reasons for its effectiveness, offering valuable insights for future research on token efficiency. Homepage: runjia.tech/iclr_tokenseek.

Deep Learning · Generative Models and Autoencoders

Xuwang Yin, Claire Zhang, Julie Steele, Nir Shavit, Tony Wang

Simultaneously achieving robust classification and high-fidelity generative modeling within a single framework presents a significant challenge. Hybrid approaches, such as Joint Energy-Based Models (JEM), interpret classifiers as EBMs but are often limited by the instability and poor sample quality inherent in training based on Stochastic Gradient Langevin Dynamics (SGLD). We address these limitations by proposing a novel training framework that integrates adversarial training (AT) principles for both discriminative robustness and stable generative learning. The proposed method introduces three key innovations: (1) the replacement of SGLD-based JEM learning with a stable, AT-based approach that optimizes the energy function through a Binary Cross-Entropy (BCE) loss that discriminates between real data and contrastive samples generated via Projected Gradient Descent (PGD); (2) adversarial training for the discriminative component that enhances classification robustness while implicitly providing the gradient regularization needed for stable EBM training; and (3) a two-stage training strategy that addresses normalization-related instabilities and enables leveraging pretrained robust classifiers, generalizing effectively across architectures. Experiments on CIFAR-10/100 and ImageNet demonstrate that our approach: (1) is the first EBM-based hybrid to scale to high-resolution datasets with high training stability, simultaneously achieving state-of-the-art discriminative and generative performance on ImageNet 256$\times$256; (2) uniquely combines generative quality with adversarial robustness, enabling faithful counterfactual explanations; and (3) functions as a competitive standalone generative model, matching autoregressive models and surpassing diffusion models while offering additional versatility.

Social Aspects · Accountability, Transparency and Interpretability

Yein Park, Jungwoo Park, Jaewoo Kang

Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when rephrased in past tense, a critical generalization gap is revealed in current alignment methods whose underlying mechanisms are poorly understood. In this work, we introduce Activation-Scaling Guard (ASGuard), an insightful, mechanistically-informed framework that surgically mitigates this specific vulnerability. In the first step, we use circuit analysis to identify the specific attention heads causally linked to the targeted jailbreaking such as a tense-changing attack. Second, we train a precise, channel-wise scaling vector to recalibrate the activation of tense vulnerable heads. Lastly, we apply it into a "preventative fine-tuning", forcing the model to learn a more robust refusal mechanism. Across four LLMs, ASGuard effectively reduces the attack success rate of targeted jailbreaking while preserving general capabilities and minimizing over refusal, achieving a Pareto-optimal balance between safety and utility. Our findings underscore how adversarial suffixes suppress the propagation of the refusal-mediating direction, based on mechanistic analysis. Furthermore, our work showcases how a deep understanding of model internals can be leveraged to develop practical, efficient, and targeted methods for adjusting model behavior, charting a course for more reliable and interpretable AI safety.

Social Aspects · Accountability, Transparency and Interpretability

An Vo, Khai-Nguyen Nguyen, Mohammad Reza Taesiri, THI TUONG VY DANG, Anh Nguyen, Daeyoung Kim

Large language models (LLMs) memorize a vast amount of prior knowledge from the Internet that helps them on downstream tasks but also may notoriously sway their outputs toward wrong or biased answers. In this work, we test how the knowledge of popular subjects hurts the accuracy of vision language models (VLMs) on standard, objective visual tasks of counting and identification. We find that state-of-the-art VLMs are strongly biased (e.g., unable to recognize that a 4th stripe has been added to a 3-stripe Adidas logo), scoring an average of 17.05% accuracy in counting (e.g., counting stripes in an Adidas-like logo) across 7 diverse domains spanning animals, logos, chess, game boards, optical illusions, and patterned grids. Removing image backgrounds nearly doubles accuracy (by 21.09 points), revealing that background visual cues trigger these biased responses. Further analysis of VLMs' reasoning patterns shows that counting accuracy initially rises with thinking tokens, reaching ~40%, before declining with model overthinking. Our work presents an interesting failure mode in VLMs and a human-supervised automated framework for testing VLM biases. Code and data are available at: vlmsarebiased.github.io.

Applications · Genetics, Cell Biology, Health, etc

Kai Zhuang, Jiawei Zhang, Yumou Liu, Hanqun Cao, Chunbin Gu, Mengdi Liu, Zhangyang Gao, Zitong Jerry Wang, Xuanhe Zhou, Pheng-Ann Heng 等

Scientific Large Language Models (Sci-LLMs) have emerged as a promising frontier for accelerating biological discovery. However, these models face a fundamental challenge when processing raw biomolecular sequences: the tokenization dilemma. Whether treating sequences as a specialized language, risking the loss of functional motif information, or as a separate modality, introducing formidable alignment challenges, current strategies fundamentally limit their reasoning capacity. We challenge this sequence-centric paradigm by positing that a more effective strategy is to provide Sci-LLMs with high-level structured context derived from established bioinformatics tools, thereby bypassing the need to interpret low-level noisy sequence data directly. Through a systematic comparison of leading Sci-LLMs on biological reasoning tasks, we tested three input modes: sequence-only, context-only, and a combination of both. Our findings are striking: the context-only approach consistently and substantially outperforms all other modes. Even more revealing, the inclusion of the raw sequence alongside its high-level context consistently degrades performance, indicating that raw sequences act as informational noise, even for models with specialized tokenization schemes. These results suggest that the primary strength of existing Sci-LLMs lies not in their nascent ability to interpret biomolecular syntax from scratch, but in their profound capacity for reasoning over structured, human-readable knowledge. Therefore, we argue for reframing Sci-LLMs not as sequence decoders, but as powerful reasoning engines over expert knowledge. This work lays the foundation for a new class of hybrid scientific AI agents, repositioning the developmental focus from direct sequence interpretation towards high-level knowledge synthesis.

Social Aspects · Accountability, Transparency and Interpretability

Yuhui Wang, Changjiang Li, Guangke Chen, Jiacheng Liang, Ting Wang

Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning. However, recent studies reveal that their final answers often contradict their own reasoning traces. We hypothesize that this inconsistency stems from two competing mechanisms for generating answers: CoT reasoning and memory retrieval. To test this hypothesis, we conduct controlled experiments that challenge LRMs with misleading cues during reasoning and/or corrupted answers during retrieval. Our results across models and datasets confirm that both mechanisms operate simultaneously, with their relative dominance influenced by multiple factors: problem domains, model scales, and fine-tuning approaches (e.g., reinforcement learning vs. distillation). The findings reveal a critical limitation in current reasoning fine-tuning paradigms: models can exploit the retrieval mechanism as a shortcut, effectively "hacking" the reward signal and undermining genuine reasoning development. To address this challenge, we introduce FARL, a novel fine-tuning framework that integrates memory unlearning with reinforcement learning. By carefully suppressing retrieval shortcuts during the fine-tuning process, FARL promotes reasoning-dominant behavior and enhances generalizable reasoning capabilities. The code is available at https://github.com/ZJUWYH/FARL.

Theory · Interpretability and Visualization

Dmytro Vitel, Anshuman Chhabra

Identifying how training samples influence/impact Large Language Model (LLM) decision-making is essential for effectively interpreting model decisions and auditing large-scale datasets. Current training sample influence estimation methods (also known as influence functions) undertake this goal by utilizing information flow through the model via its first-order and higher-order gradient terms. However, owing to the large model sizes of today consisting of billions of parameters, these influence computations are often restricted to some subset of model layers to ensure computational feasibility. Prior seminal work by Yeh et al. (2022) in assessing which layers are best suited for computing language data influence concluded that the first (embedding) layers are the most informative for this purpose, using a hypothesis based on influence scores canceling out (i.e., the cancellation effect). In this work, we propose theoretical and empirical evidence demonstrating how the cancellation effect is unreliable, and that middle attention layers are better estimators for influence. Furthermore, we address the broader challenge of aggregating influence scores across layers, and showcase how alternatives to standard averaging (such as ranking and vote-based methods) can lead to significantly improved performance. Finally, we propose better methods for evaluating influence score efficacy in LLMs without undertaking model retraining, and propose a new metric known as the Noise Detection Rate (NDR) that exhibits strong predictive capability compared to the cancellation effect. Through extensive experiments across LLMs of varying types and scales, we concretely determine that the first (layers) are not necessarily better than the last (layers) for LLM influence estimation, contrasting with prior knowledge in the field.

Social Aspects · Trustworthy Machine Learning

Xinran Xu, Xiuyi Fan

Accurate estimation of uncertainty in deep learning is critical for deploying models in high-stakes domains such as medical diagnosis and autonomous decision-making, where overconfident predictions can lead to harmful outcomes. In practice, understanding the reason behind a model’s uncertainty and the type of uncertainty it represents can support risk-aware decisions, enhance user trust, and guide additional data collection. However, many existing methods only address a single type of uncertainty or require modifications and retraining of the base model, making them difficult to adopt in real-world systems. We introduce CUPID (Comprehensive Uncertainty Plug-in estImation moDel), a general-purpose module that jointly estimates aleatoric and epistemic uncertainty without modifying or retraining the base model. CUPID can be flexibly inserted into any layer of a pretrained network. It models aleatoric uncertainty through a learned Bayesian identity mapping and captures epistemic uncertainty by analyzing the model’s internal responses to structured perturbations. We evaluate CUPID across a range of tasks, including classification, regression, and out-of-distribution detection. The results show that it consistently delivers competitive performance while offering layer-wise insights into the origins of uncertainty. By making uncertainty estimation modular, interpretable, and model-agnostic, CUPID supports more transparent and trustworthy AI.

Applications · Genetics, Cell Biology, Health, etc

Suyi Chen, Haibin Ling

As a critical modality for structural biology, cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution. The core computational task in single-particle cryo-EM is to reconstruct the 3D electrostatic potential of a molecule from noisy 2D projections acquired at unknown orientations. Gaussian mixture models (GMMs) provide a continuous, compact, and physically interpretable representation for molecular density and have recently gained interest in cryo-EM reconstruction. However, existing methods rely on external consensus maps or atomic models for initialization, limiting their use in self-contained pipelines. In parallel, differentiable rendering techniques such as Gaussian splatting have demonstrated remarkable scalability and efficiency for volumetric representations, suggesting a natural fit for GMM-based cryo-EM reconstruction. However, off-the-shelf Gaussian splatting methods are designed for photorealistic view synthesis and remain incompatible with cryo-EM due to mismatches in the image formation physics, reconstruction objectives, and coordinate systems. Addressing these issues, we propose **cryoSplat**, a GMM-based method that integrates Gaussian splatting with the physics of cryo-EM image formation. In particular, we develop an orthogonal projection-aware Gaussian splatting, with adaptations such as a view-dependent normalization term and FFT-aligned coordinate system tailored for cryo-EM imaging. These innovations enable stable and efficient homogeneous reconstruction directly from raw cryo-EM particle images using random initialization. Experimental results on real datasets validate the effectiveness and robustness of cryoSplat over representative baselines. The code will be released at https://github.com/Chen-Suyi/cryosplat.

Applications · Time Series

Beomjun Bark, Yun Kwan Kim

Accurate detection of clinically meaningful events in healthcare time-series data is crucial for reliable downstream analysis and decision support. However, most existing methods struggle to jointly localize event boundaries and classify event types; even detection transformer (DETR)-based approaches show limited performance when confronted with extremely sparse events typical of clinical recordings. To address these challenges, we propose a coarse-to-fine detection framework combining a global context explorer, a local detail inspector, and an adaptive gating module (AGM) that fuses multiple label perspectives. The AGM uses transformed labels—encoding event presence and temporal position—to improve learning on sparse events. This design acts as a switch that selectively activates detailed feature extraction only when an event is likely, thereby reducing noise and improving efficiency in sparse settings. We evaluate our framework on diverse healthcare datasets—including arrhythmia detection, emotion recognition, and human-activity monitoring—and demonstrate substantial performance gains over existing DETR-based models, with particularly strong improvements in sparse event detection. With precise and robust event detection, our framework enables interpretation and actionable insights in real-world clinical applications.

Social Aspects · Accountability, Transparency and Interpretability

Ruimeng Ye, Zihan Wang, Zinan Ling, Yang Xiao, Manling Li, Xiaolong Ma, Bo Hui

Humans shift between different personas depending on social context. Large Language Models (LLMs) demonstrate a similar flexibility in adopting different personas and behaviors. Existing approaches, however, typically adapt such behavior through external knowledge such as prompting, retrieval-augmented generation (RAG), or fine-tuning. We ask: do LLMs really need external context or parameters to adapt to different behaviors, or do they already have such knowledge embedded in their parameters? In this work, we show that LLMs already contain persona-specialized subnetworks in their parameter space. Using small calibration datasets, we identify distinct activation signatures associated with different personas. Guided by these statistics, we develop a masking strategy that isolates lightweight persona subnetworks. Building on the findings, we further discuss: how can we discover opposing subnetworks from the model that lead to binary-opposing personas, such as introvert-extrovert? To further enhance separation in binary opposition scenarios, we introduce a contrastive pruning strategy that identifies parameters responsible for the statistical divergence between opposing personas. Our method is entirely training-free and relies solely on the language model's existing parameter space. Across diverse evaluation settings, the resulting subnetworks exhibit significantly stronger persona alignment than baselines that require external knowledge while being more efficient. Our findings suggest that diverse human-like behaviors are not merely induced in LLMs, but are already embedded in their parameter space—pointing toward a new perspective on controllable and interpretable personalization in large language models. Our code is available at https://github.com/Ruimeng-Ye/Persona.git.

General Machine Learning · Representation Learning

Geunhyeok Yu, Sunjae Jeong, Yoonyoung Choi, Jaeseung Kim, Hyoseok Hwang

Vision Transformers are widely adopted as the backbone of vision foundation models, but they are known to produce high-norm artifacts that degrade representation quality. When knowledge distillation transfers these features to students, high-norm artifacts dominate the objective, so students overfit to artifacts and underweight informative signals, diminishing the gains from larger models. Prior work attempted to remove artifacts but encountered an inherent trade-off between artifact suppression and preserving informative signals from teachers. To address this, we introduce Singular Nullspace-Guided Energy Reallocation (SiNGER), a novel distillation framework that suppresses artifacts while preserving informative signals. The key idea is principled teacher feature refinement: during refinement, we leverage the nullspace-guided perturbation to preserve information while suppressing artifacts. Then, the refined teacher's features are distilled to a student. We implement this perturbation efficiently with a LoRA-based adapter that requires minimal structural modification. Extensive experiments show that SiNGER consistently improves student models, achieving state-of-the-art performance in multiple downstream tasks and producing clearer and more interpretable representations.