arXiv subjects

Kowshik Thopalli

Publications and source records attributed to Kowshik Thopalli.

At least 19 recordsLinked to original sources

arXiv2026

Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching

Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the same up to some class of transformations. While there exists many methods for alignment between different latent spaces, it is typically done using a set of shared sample correspondences, known as anchors. This leaves a fundamental question: are the geometric signatures of different latent spaces representing similar data sufficient to recover an alignment between them? To that end, we introduce HGA (Hyperspherical Gaussian Alignment), a method that directly optimizes a transformation between two latent spaces by maximizing a geometric measure of "fit" between them. Since it is driven by the geometry of the latent spaces rather than paired data, HGA can operate in both an unsupervised and weakly supervised regime. On tasks such as model stitching or multilingual word embedding correspondence recovery, HGA manages to match supervised results with minimal or no supervision.

cs.LG↗

arXiv2026

The Anatomy of Uncertainty in LLMs

Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment. Current approaches, which either provide a single uncertainty score or rely on the classical aleatoric-epistemic dichotomy, fail to offer actionable insights for improving the generative model. Recent studies have also shown that such methods are not enough for understanding uncertainty in LLMs. In this work, we advocate for an uncertainty decomposition framework that dissects LLM uncertainty into three distinct semantic components: (i) input ambiguity, arising from ambiguous prompts; (ii) knowledge gaps, caused by insufficient parametric evidence; and (iii) decoding randomness, stemming from stochastic sampling. Through a series of experiments we demonstrate that the dominance of these components can shift across model size and task. Our framework provides a better understanding to audit LLM reliability and detect hallucinations, paving the way for targeted interventions and more trustworthy systems.

cs.AI↗

arXiv2026

The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model families. We present the first large-scale evaluation of CoT monitorability across 13 diverse languages and seven frontier model families, comprising 16 models. Using adversarial-hint evaluations that require explicit intermediate computation, together with analysis of internal answer-token probabilities, we consistently find CoT unfaithfulness across languages and hint types, with an average rate of 95.9\% across 8B--120B parameter models. We find that frontier models systematically engage in strategic manipulation, including answer-switching, post-hoc rationalization, and procedural exploitation of hints, making external monitors struggle to detect deception. We show that frontier models often commit to the misaligned cue in their latent activations within the first 15\% of generation, even when the CoT appears faithful. Surprisingly, these deceptive patterns remain 100\% in low-resource languages, revealing fundamental limitations in current CoT-based oversight. Our results reveal that CoT monitoring is fundamentally fragile under linguistic distribution shift, providing a substantially weaker safety signal than what English-only studies suggest. These findings underscore an urgent need to develop robust CoT monitors and to accelerate research into white-box monitoring techniques, especially to improve CoT monitorability in mid- and low-resource languages. Our code is available \href{https://multilingual-cot-monitoring.github.io/}{\textcolor{blue}{here}}.

cs.CL↗

arXiv2026

LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images

We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By combining sparse autoencoder-based divergence testing with density ratio estimation, LatentDiff identifies interpretable semantic differences between datasets at a fraction of the computational cost of caption-based alternatives. We also introduce Noisy-Diff, a benchmark capturing realistic sparse distribution shifts that cause existing methods to struggle. Experiments demonstrate that LatentDiff achieves superior accuracy while remaining robust to settings where an extremely small fraction of images (from 5% to <1% ) differ semantically.

cs.CV↗

arXiv2026

Improving Robustness In Sparse Autoencoders via Masked Regularization

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability to project LLM activations onto sparse latent spaces. However, sparsity alone is an imperfect proxy for interpretability, and current training objectives often result in brittle latent representations. SAEs are known to be prone to feature absorption, where general features are subsumed by more specific ones due to co-occurrence, degrading interpretability despite high reconstruction fidelity. Recent negative results on Out-of-Distribution (OOD) performance further underscore broader robustness related failures tied to under-specified training objectives. We address this by proposing a masking-based regularization that randomly replaces tokens during training to disrupt co-occurrence patterns. This improves robustness across SAE architectures and sparsity levels reducing absorption, enhancing probing performance, and narrowing the OOD gap. Our results point toward a practical path for more reliable interpretability tools.

cs.LG↗

arXiv2026

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders

Sparse autoencoders (SAEs) promise a unified approach for mechanistic interpretability, concept discovery, and model steering in LLMs and LVLMs. However, realizing this potential requires learned features to be both interpretable and steerable. To that end, we introduce two new computationally inexpensive interpretability and steerability metrics for a systematic analysis of LVLM SAEs. This uncovers two observations; (i) a majority of SAE neurons exhibit either low interpretability or low steerability or both, rendering them ineffective for downstream use; and (ii) user-desired concepts are often absent in the SAE, thus limiting their practical utility. To address these limitations, we propose Concept Bottleneck Sparse Autoencoders (CB-SAE) - a novel post-hoc framework that prunes low-utility neurons and augments the latent space with a lightweight concept bottleneck aligned to a user-defined concept set. The resulting CB-SAE improves interpretability by +32.1% and steerability by +14.5% across LVLMs and image generation tasks.

cs.LG↗

arXiv2026

ProtAlign: Contrastive learning paradigm for Sequence and structure alignment

Protein language models often take into consideration the alignment between a protein sequence and its textual description. However, they do not take structural information into consideration. Traditional methods treat sequence and structure separately, limiting the ability to exploit the alignment between the structure and protein sequence embeddings. In this paper, we introduce a sequence structure contrastive alignment framework, which learns a shared embedding space where proteins are represented consistently across modalities. By training on large-scale pairs of sequences and experimentally resolved or predicted structures, the model maximizes agreement between matched sequence structure pairs while pushing apart unrelated pairs. This alignment enables cross-modal retrieval (e.g., finding structural neighbors given a sequence), improves downstream prediction tasks such as function annotation and stability estimation, and provides interpretable links between sequence variation and structural organization. Our results demonstrate that contrastive learning can serve as a powerful bridge between protein sequences and structures, offering a unified representation for understanding and engineering proteins.

cs.LG↗

arXiv2025

Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive exploration intractable. While conventional embedding techniques such as UMAP can reveal global structure, they suffer from limitations including high-dimensional compression artifacts, overplotting, and misleading neighborhood distortions. In this work, we propose a focused exploration framework that prioritizes curated concepts and their corresponding SAE features over attempts to visualize all available features simultaneously. We present an interactive visualization system that combines topology-based visual encoding with dimensionality reduction to faithfully represent both local and global relationships among selected features. This hybrid approach enables users to investigate SAE behavior through targeted, interpretable subsets, facilitating deeper and more nuanced analysis of concept representation in latent space.

cs.CL↗

arXiv2025

On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation

LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve both the quality and efficiency of data generation. To test this hypothesis, we explore three prompt construction protocols: Expert-guided, LLM-guided, and Novel-Mapping. Through empirical studies with the recently proposed GReaT framework, we find that context-enriched prompts lead to significantly improved data generation quality and training efficiency.

cs.CL↗

arXiv2025

Leveraging Registers in Vision Transformers for Robust Adaptation

Vision Transformers (ViTs) have shown success across a variety of tasks due to their ability to capture global image representations. Recent studies have identified the existence of high-norm tokens in ViTs, which can interfere with unsupervised object discovery. To address this, the use of "registers" which are additional tokens that isolate high norm patch tokens while capturing global image-level information has been proposed. While registers have been studied extensively for object discovery, their generalization properties particularly in out-of-distribution (OOD) scenarios, remains underexplored. In this paper, we examine the utility of register token embeddings in providing additional features for improving generalization and anomaly rejection. To that end, we propose a simple method that combines the special CLS token embedding commonly employed in ViTs with the average-pooled register embeddings to create feature representations which are subsequently used for training a downstream classifier. We find that this enhances OOD generalization and anomaly rejection, while maintaining in-distribution (ID) performance. Extensive experiments across multiple ViT backbones trained with and without registers reveal consistent improvements of 2-4\% in top-1 OOD accuracy and a 2-3\% reduction in false positive rates for anomaly detection. Importantly, these gains are achieved without additional computational overhead.

cs.CV↗

arXiv2024

Physics-Informed Transformation Toward Improving the Machine-Learned NLTE Models of ICF Simulations

The integration of machine learning techniques into Inertial Confinement Fusion (ICF) simulations has emerged as a powerful approach for enhancing computational efficiency. By replacing the costly Non-Local Thermodynamic Equilibrium (NLTE) model with machine learning models, significant reductions in calculation time have been achieved. However, determining how to optimize machine learning-based NLTE models in order to match ICF simulation dynamics remains challenging, underscoring the need for physically relevant error metrics and strategies to enhance model accuracy with respect to these metrics. Thus, we propose novel physics-informed transformations designed to emphasize energy transport, use these transformations to establish new error metrics, and demonstrate that they yield smaller errors within reduced principal component spaces compared to conventional transformations.

physics.plasm-ph↗

arXiv2024

DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation

Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that leverages priors from large language models (LLMs) and vision-language models (VLMs) to detect failures in image classification models. DECIDER utilizes LLMs to specify task-relevant core attributes and constructs a ``debiased'' version of the classifier by aligning its visual features to these core attributes using a VLM, and detects potential failure by measuring disagreement between the original and debiased models. In addition to proactively identifying samples on which the model would fail, DECIDER also provides human-interpretable explanations for failure through a novel attribute-ablation strategy. Through extensive experiments across diverse benchmarks spanning subpopulation shifts (spurious correlations, class imbalance) and covariate shifts (synthetic corruptions, domain shifts), DECIDER consistently achieves state-of-the-art failure detection performance, significantly outperforming baselines in terms of the overall Matthews correlation coefficient as well as failure and success recall. Our codes can be accessed at~\url{https://github.com/kowshikthopalli/DECIDER/}

cs.CV↗

arXiv2024

Speeding Up Image Classifiers with Little Companions

Scaling up neural networks has been a key recipe to the success of large language and vision models. However, in practice, up-scaled models can be disproportionately costly in terms of computations, providing only marginal improvements in performance; for example, EfficientViT-L3-384 achieves <2% improvement on ImageNet-1K accuracy over the base L1-224 model, while requiring $14\times$ more multiply-accumulate operations (MACs). In this paper, we investigate scaling properties of popular families of neural networks for image classification, and find that scaled-up models mostly help with "difficult" samples. Decomposing the samples by difficulty, we develop a simple model-agnostic two-pass Little-Big algorithm that first uses a light-weight "little" model to make predictions of all samples, and only passes the difficult ones for the "big" model to solve. Good little companion achieve drastic MACs reduction for a wide variety of model families and scales. Without loss of accuracy or modification of existing models, our Little-Big models achieve MACs reductions of 76% for EfficientViT-L3-384, 81% for EfficientNet-B7-600, 71% for DeiT3-L-384 on ImageNet-1K. Little-Big also speeds up the InternImage-G-512 model by 62% while achieving 90% ImageNet-1K top-1 accuracy, serving both as a strong baseline and as a simple practical method for large model compression.

cs.CV↗

arXiv2024

On the Use of Anchoring for Training Vision Models

Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically explore anchoring as a general protocol for training vision models, providing fundamental insights into its training and inference processes and their implications for generalization and safety. Despite its promise, we identify a critical problem in anchored training that can lead to an increased risk of learning undesirable shortcuts, thereby limiting its generalization capabilities. To address this, we introduce a new anchored training protocol that employs a simple regularizer to mitigate this issue and significantly enhances generalization. We empirically evaluate our proposed approach across datasets and architectures of varying scales and complexities, demonstrating substantial performance gains in generalization and safety metrics compared to the standard training protocol.

cs.LG↗

arXiv2023

Target-Aware Generative Augmentations for Single-Shot Adaptation

In this paper, we address the problem of adapting models from a source domain to a target domain, a task that has become increasingly important due to the brittle generalization of deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic toolbox data augmentations in cases of limited target data availability. We consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA, which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments on a variety of benchmarks, distribution shifts and image corruptions, we find that SiSTA produces significantly improved generalization over existing baselines in face attribute detection and multi-class object recognition. Furthermore, SiSTA performs competitively to models obtained by training on larger target datasets. Our codes can be accessed at https://github.com/Rakshith-2905/SiSTA.

cs.CV↗

arXiv2022

Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization

Domain generalization (DG) methods aim to develop models that generalize to settings where the test distribution is different from the training data. In this paper, we focus on the challenging problem of multi-source zero shot DG (MDG), where labeled training data from multiple source domains is available but with no access to data from the target domain. A wide range of solutions have been proposed for this problem, including the state-of-the-art multi-domain ensembling approaches. Despite these advances, the naïve ERM solution of pooling all source data together and training a single classifier is surprisingly effective on standard benchmarks. In this paper, we hypothesize that, it is important to elucidate the link between pre-specified domain labels and MDG performance, in order to explain this behavior. More specifically, we consider two popular classes of MDG algorithms -- distributional robust optimization (DRO) and multi-domain ensembles, in order to demonstrate how inferring custom domain groups can lead to consistent improvements over the original domain labels that come with the dataset. To this end, we propose (i) Group-DRO++, which incorporates an explicit clustering step to identify custom domains in an existing DRO technique; and (ii) DReaME, which produces effective multi-domain ensembles through implicit domain re-labeling with a novel meta-optimization algorithm. Using empirical studies on multiple standard benchmarks, we show that our variants consistently outperform ERM by significant margins (1.5% - 9%), and produce state-of-the-art MDG performance. Our code can be found at https://github.com/kowshikthopalli/DREAME

cs.LG↗

arXiv2022

Single-Shot Domain Adaptation via Target-Aware Generative Augmentation

The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic data augmentations in cases of limited target data availability. In this paper, we consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA (Single-Shot Target Augmentations), which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments with a state-of-the-art domain adaptation method, we find that SiSTA produces improvements as high as 20\% over existing baselines under challenging shifts in face attribute detection, and that it performs competitively to oracle models obtained by training on a larger target dataset.

cs.CV↗

arXiv2022

Domain Alignment Meets Fully Test-Time Adaptation

A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled data. In this paper, we focus on a challenging variant of this problem, where access to the original source data is restricted. While fully test-time adaptation (FTTA) and unsupervised domain adaptation (UDA) are closely related, the advances in UDA are not readily applicable to TTA, since most UDA methods require access to the source data. Hence, we propose a new approach, CATTAn, that bridges UDA and FTTA, by relaxing the need to access entire source data, through a novel deep subspace alignment strategy. With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation. Through extensive experimental evaluation on multiple 2D and 3D vision benchmarks (ImageNet-C, Office-31, OfficeHome, DomainNet, PointDA-10) and model architectures, we demonstrate significant gains in FTTA performance. Furthermore, we make a number of crucial findings on the utility of the alignment objective even with inherently robust models, pre-trained ViT representations and under low sample availability in the target domain.

cs.CV↗