Research: Learning Algorithms and Optimization

Past Projects Patents Publications Funding Agencies

Learning Algorithms and Optimization

(Return to Current Research Outline)

F. Generative AI

Our research in Generative AI develops efficient, reliable, and controllable foundation models spanning large language models and diffusion models. We investigate algorithmic advances that improve model efficiency, reasoning, continual learning, safety, and controllability, while enabling practical deployment of state-of-the-art generative models across diverse applications.

1. Large Language Models

Our work on Large Language Models (LLMs) focuses on improving both efficiency and reasoning capabilities. We develop methods for memory-efficient training, pruning, continual learning, and data-efficient instruction tuning, alongside agentic frameworks, structured reasoning, and robust prompt-based learning, enabling scalable and reliable LLM deployment.

Publications (Efficiency):
  1. Choudhary, Sakshi, Utkarsh Saxena, and Kaushik Roy. "OASIS: Online Activation Subspace Learning for Memory-Efficient Training." ArXiv, 2026.

    Abstract: Training large language models (LLMs) is constrained by memory requirements, with activations accounting for a substantial fraction of the total footprint. Existing approaches reduce memory using low-rank weight parameterizations or low-rank gradient subspaces for optimizer states, while activation memory is addressed through architectural modifications or compression schemes based on periodically updated projections. We propose OASIS, an online activation subspace learning algorithm for memory-efficient training that tracks and continuously updates a low-dimensional activation subspace during training. Intermediate activations are projected onto this evolving subspace, reducing memory without modifying forward-pass computations. The evolving activation subspace induces low-rank gradient representations, enabling both gradients and optimizer states to be maintained directly in this subspace, while a projection-aware optimizer consistently transports optimizer states across subspace updates for stable training. Across various finetuning and pretraining tasks, OASIS achieves up to 2× lower peak memory than full fine-tuning while matching its performance and outperforming prior low-rank methods.

  2. Malettira, Prajna G., Manish Nagaraj, Arjun Roy, Shubham Negi, Kaushik Roy. "TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation." ArXiv, 2026.

    Abstract: Structured pruning is essential for efficient deployment of Large Language Models (LLMs). The varying sensitivity of LLM sub-blocks to pruning necessitates the identification of optimal non-uniformly pruned models. Existing methods evaluate the importance of layers, attention heads, or weight channels in isolation. Such localized focus ignores the complex global structural dependencies that exist across the model. Training-aware structured pruning addresses global dependencies, but its computational cost can be just as expensive as post-pruning training. To alleviate the computational burden of training-aware pruning and capture global structural dependencies, we propose TraceNAS, a training-free Neural Architecture Search (NAS) framework that jointly explores structured pruning of LLM depth and width. TraceNAS identifies pruned models that maintain a high degree of loss landscape alignment with the pretrained model using a scale-invariant zero-shot proxy, effectively selecting models that exhibit maximal performance potential during post-pruning training. TraceNAS is highly efficient, enabling high-fidelity discovery of pruned models on a single GPU in 8.5 hours, yielding a 10× reduction in GPU-hours compared to training-aware methods. Evaluations on the Llama and Qwen families demonstrate that TraceNAS is competitive with training-aware baselines across commonsense and reasoning benchmarks.

  3. Biswas, Shristi Das, Yue Zhang, Anwesan Pal, Radhika Bhargava, Kaushik Roy. "ELLA: Efficient Lifelong Learning for Adapters in Large Language Models." European Chapter of the Association for Computational Linguistics (EACL), 2026.

    Abstract: Large Language Models (LLMs) suffer severe catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing approaches are fundamentally limited: replay-based methods are impractical and privacy-violating, while strict orthogonality-based methods collapse under scale: each new task is projected onto an orthogonal complement, progressively reducing the residual degrees of freedom and eliminating forward transfer by forbidding overlap in shared representations. In this work, we introduce ELLA, a training framework built on the principle of selective subspace de-correlation. Rather than forbidding all overlap, ELLA explicitly characterizes the structure of past updates and penalizes alignments along their high-energy, task-specific directions, while preserving freedom in the low-energy residual subspaces to enable transfer. Formally, this is realized via a lightweight regularizer on a single aggregated update matrix. We prove this mechanism corresponds to an anisotropic shrinkage operator that bounds interference, yielding a penalty that is both memory- and compute-constant regardless of task sequence length. ELLA requires no data replay, no architectural expansion, and negligible storage. Empirically, it achieves state-of-the-art CL performance on three popular benchmarks, with relative accuracy gains of up to 9.6% and a 35× smaller memory footprint. Further, ELLA scales robustly across architectures and actively enhances the model's zero-shot generalization performance on unseen tasks, establishing a principled and scalable solution for constructive lifelong LLM adaptation.

  4. Nagaraj, Manish, Sakshi Choudhary, Utkarsh Saxena, Deepak Ravikumar, Kaushik Roy. "TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning." International Conference on Machine Learning (ICML), 2026.

    Abstract: Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior results, though curating them remains challenging. Existing methods often rely on coarse, sample-level signals like gradients, an approach that is computationally expensive and overlooks fine-grained features. To address this, we introduce TRIM (Token Relevance via Interpretable Multi-layer Attention), a forward-only, token-centric framework. Instead of using gradients, TRIM operates by matching underlying representational patterns identified via attention-based "fingerprints" from a handful of target samples. Such an approach makes TRIM highly efficient and uniquely sensitive to the structural features that define a task. Coresets selected by our method consistently outperform state-of-the-art baselines by up to 9% on downstream tasks and even surpass the performance of full-data fine-tuning in some settings. By avoiding expensive backward passes, TRIM achieves this at a fraction of the computational cost. These findings establish TRIM as a scalable and efficient alternative for building high-quality instruction-tuning datasets.

Publications (Agentic AI):
  1. He, Kang, and Kaushik Roy. "SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution." ArXiv, 2026.

    Abstract: Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context management for accurate localization, and (2) systematic approaches for iterative, test-driven code modification to resolve issues. To address these challenges, we propose SWE-Adept, an LLM-based two-agent framework where a localization agent identifies issue-relevant code locations and a resolution agent implements the corresponding fixes. For issue localization, we introduce agent-directed depth-first search that selectively traverses code dependencies. This minimizes issue-irrelevant content in the agent's context window and improves localization accuracy. For issue resolution, we employ adaptive planning and structured problem solving. We equip the agent with specialized tools for progress tracking and Git-based version control. These tools interface with a shared working memory that stores code-state checkpoints indexed by execution steps, facilitating precise checkpoint retrieval. This design enables reliable agent-driven version-control operations for systematic issue resolution, including branching to explore alternative solutions and reverting failed edits. Experiments on SWE-Bench Lite and SWE-Bench Pro demonstrate that SWE-Adept consistently outperforms prior approaches in both issue localization and resolution, improving the end-to-end resolve rate by up to 4.3%.

  2. He, Kang, and Kaushik Roy. "LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models." Empirical Methods in Natural Language Processing (EMNLP), 2025.

    Abstract: Large language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration and the maintenance of logical coherence and (2) searching the right combination of premises at each reasoning step is inherently challenging in tasks with large premise space. To address this, we propose LogicTree, an inference-time modular framework employing algorithm-guided search to automate structured proof exploration and ensure logical coherence. Advancing beyond tree-of-thought (ToT), we incorporate caching mechanism into LogicTree to enable effective utilization of historical knowledge, preventing reasoning stagnation and minimizing redundancy. Furthermore, we address the combinatorial complexity of premise search by decomposing it into a linear process. The refined premise selection restricts subsequent inference to at most one derivation per step, enhancing reasoning granularity and enforcing strict step-by-step reasoning. Additionally, we introduce two LLM-free heuristics for premise prioritization, enabling strategic proof search. Experimental results on five datasets demonstrate that LogicTree optimally scales inference-time computation to achieve higher proof accuracy, surpassing chain-of-thought (CoT) and ToT with average gains of 23.6% and 12.5%, respectively, on GPT-4o. Moreover, within LogicTree, GPT-4o outperforms o3-mini by 7.6% on average.

  3. He, Kang, Yinghan Long, and Kaushik Roy. "Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models." Findings of the Association for Computational Linguistics (EMNLP Findings), 2024.

    Abstract: Prompt-based learning is susceptible to intrinsic bias present in pre-trained language models (LMs), leading to sub-optimal performance in prompt-based zero/few-shot settings. In this work, we propose a null-input prompting method to calibrate intrinsic bias encoded in pre-trained LMs. Different from prior efforts that address intrinsic bias primarily for social fairness and often involve excessive computational cost, our objective is to explore enhancing LMs?performance in downstream zero/fewshot learning while emphasizing the efficiency of intrinsic bias calibration. Specifically, we leverage a diverse set of auto-selected nullmeaning inputs generated from GPT-4 to probe intrinsic bias of pre-trained LMs. Utilizing the bias-reflected probability distribution, we formulate a distribution disparity loss for bias calibration, where we exclusively update bias parameters (0.1% of total parameters) of LMs towards equal probability distribution. Experimental results show that the calibration promotes an equitable starting point for LMs while preserving language modeling abilities. Across a wide range of datasets, including sentiment analysis and topic classification, our method significantly improves zero/few-shot learning performance of LMs for both in-context learning and prompt-based fine-tuning (on average 9%and 2%, respectively)..

2. Diffusion Models

Our research on Diffusion Models focuses on developing efficient and controllable generative models. We investigate training-free model compression, concept editing and unlearning, and representation-aware control techniques that improve safety, interpretability, and deployment efficiency while preserving generation quality.

Publications (Concept Unlearning/Control):
  1. Roy, Arani, Shristi Das Biswas, Kaushik Roy. "HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models." ArXiv, 2026.

    Abstract: Text-to-image diffusion models can generate visually stunning images, yet, controlling what appears and how it appears, remains surprisingly difficult, especially when operating solely within the constraints of the text-conditioning space. For example, changing a subject or adjusting an attribute often leads to unintended side effects, such as altered backgrounds or distorted details. This is because most existing text-based control methods treat the embedding space as Euclidean and apply simple linear transformations, which do not reflect how semantic concepts are actually organized. In this work, we take a step back and ask: what is the true geometry of these embeddings? We find that text encoder representations lie on a hypersphere, where concepts are not linear directions but structured, anisotropic distributions better captured by Kent distributions. Building on this insight, we propose HEART, a training-free framework that performs Kent-aware geodesic transformations directly on the hypersphere. By respecting the underlying geometry, HEART enables intuitive and precise edits, such as consistent subject replacement and fine-grained attribute control, while preserving the original scene. Importantly, HEART requires no finetuning, inversion, or optimization, and generalizes across diffusion model architectures. Our results show that a simple shift in perspective, from linear to spherical, can unlock fast, and controllable image generation.

  2. Biwas, Shristi Das, Arani Roy, Kaushik Roy. "Now You See It, Now You Don't: Instant Concept Erasure for Safe Text-to-Image and Video Generation." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Findings), 2026.

    Abstract: Robust concept removal for text-to-image (T2I) and text-to-video (T2V) models is essential for their safe deployment. Existing methods, however, suffer from costly retraining, inference overhead, or vulnerability to adversarial attacks. Crucially, they rarely model the latent semantic overlap between the target erase concept and surrounding content -- causing collateral damage post-erasure -- and even fewer methods work reliably across both T2I and T2V domains. We introduce Instant Concept Erasure (ICE), a training-free, modality-agnostic, one-shot weight modification approach that achieves precise, persistent unlearning with zero overhead. ICE defines erase and preserve subspaces using anisotropic energy-weighted scaling, then explicitly regularizes against their intersection using a unique, closed-form overlap projector. We pose a convex and Lipschitz-bounded Spectral Unlearning Objective, balancing erasure fidelity and intersection preservation, that admits a stable and unique analytical solution. This solution defines a dissociation operator that is translated to the model's text-conditioning layers, making the edit permanent and runtime-free. Across targeted removals of artistic styles, objects, identities, and explicit content, ICE efficiently achieves strong erasure with improved robustness to red-teaming, all while causing only minimal degradation of original generative abilities in both T2I and T2V models.

  3. Biswas, Shristi Das*, Arani Roy*, Kaushik Roy. "CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models." Advances in Neural Information Processing Systems (NeurIPS), 2026.

    Abstract: As Text-to-Image models continue to evolve, so does the risk of generating unsafe, copyrighted, or privacy-violating content. Existing safety interventions - ranging from training data curation and model fine-tuning to inference-time filtering and guidance - often suffer from incomplete concept removal, susceptibility to jail-breaking, computational inefficiency, or collateral damage to unrelated capabilities. In this paper, we introduce CURE, a training-free concept unlearning framework that operates directly in the weight space of pre-trained diffusion models, enabling fast, interpretable, and highly specific suppression of undesired concepts. At the core of our method is the Spectral Eraser, a closed-form, orthogonal projection module that identifies discriminative subspaces using Singular Value Decomposition over token embeddings associated with the concepts to forget and retain. Intuitively, the Spectral Eraser identifies and isolates features unique to the undesired concept while preserving safe attributes. This operator is then applied in a single step update to yield an edited model in which the target concept is effectively unlearned - without retraining, supervision, or iterative optimization. To balance the trade-off between filtering toxicity and preserving unrelated concepts, we further introduce an Expansion Mechanism for spectral regularization which selectively modulates singular vectors based on their relative significance to control the strength of forgetting. All the processes above are in closed-form, guaranteeing extremely efficient erasure in only 2 seconds. Benchmarking against prior approaches, CURE achieves a more efficient and thorough removal for targeted artistic styles, objects, identities, or explicit content, with minor damage to original generation ability and demonstrates enhanced robustness against red-teaming. Project Page at \url{https://sites.google.com/view/cure-unlearning/home}.

Publications (Efficiency):
  1. Roy, Arani*, Shristi Das Biswas*, Kaushik Roy. "SlimDiff: Training-Free, Activation-Guided Hands-free Slimming of Diffusion Models." ArXiv, 2025.

    Abstract: Diffusion models (DMs), lauded for their generative performance, are computationally prohibitive due to their billion-scale parameters and iterative denoising dynamics. Existing efficiency techniques, such as quantization, timestep reduction, or pruning, offer savings in compute, memory, or runtime but are strictly bottlenecked by reliance on fine-tuning or retraining to recover performance. In this work, we introduce SlimDiff, an automated activation-informed structural compression framework that reduces both attention and feedforward dimensionalities in DMs, while being entirely gradient-free. SlimDiff reframes DM compression as a spectral approximation task, where activation covariances across denoising timesteps define low-rank subspaces that guide dynamic pruning under a fixed compression budget. This activation-aware formulation mitigates error accumulation across timesteps by applying module-wise decompositions over functional weight groups: query--key interactions, value--output couplings, and feedforward projections, rather than isolated matrix factorizations, while adaptively allocating sparsity across modules to respect the non-uniform geometry of diffusion trajectories. SlimDiff achieves up to 35\% acceleration and 100M parameter reduction over baselines, with generation quality on par with uncompressed models without any backpropagation. Crucially, our approach requires only about 500 calibration samples, over 70 fewer than prior methods. To our knowledge, this is the first closed-form, activation-guided structural compression of DMs that is entirely training-free, providing both theoretical clarity and practical efficiency.

3. Vision-Language Models

Our research on Vision-Language Models (VLMs) focuses on improving the efficiency and effectiveness of multimodal learning. We investigate data-efficient instruction tuning, multimodal alignment and grounding, and representation-aware data selection techniques that reduce training cost while preserving diverse visual reasoning capabilities.

Publications:
  1. Biswas, Shristi Das, and Kaushik Roy. "MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models." ArXiv, 2026.

    Abstract: Instruction tuning of large vision-language models (LVLMs) increasingly depends on massive multimodal corpora, yet these datasets contain samples with substantial redundancy, low visual dependency, and highly imbalanced coverage of multimodal reasoning behaviors. As a result, uniform subsampling or naive score-based selection often yields suboptimal training subsets. We introduce MAGIC, a training-free, forward-only coreset selection method designed to construct compact yet behaviorally faithful subsets for multimodal instruction tuning. MAGIC is built on three intrinsic signals extracted from a pretrained VLM: Multimodal Gain, which measures the likelihood improvement obtained from visual input; Bridging Relevance, which captures the sharpness of answer-token grounding over visual tokens; and Skill-Neuron Signatures, which characterize the functional computation elicited by each sample via top-activated feed-forward neurons. MAGIC combines these signals in a three-stage pipeline: filtering low-gain examples, ranking candidates by a normalized quality objective, and performing bucket-wise budget allocation over discrete neuron signatures to preserve latent multimodal skill coverage. This formulation avoids backpropagation, auxiliary selector training, and expensive clustering in continuous activation spaces, while remaining efficient and easily deployable in existing VLMs. Across LLaVA-665K and Vision-Flan datasets, and transfer settings to large target models, LLaVA-1.5-7B and -13B, MAGIC consistently improves over strong baselines under matched 20% budgets: it achieves 100.3% relative performance to full finetuning on LLaVA-665K and 101.6% relative performance on Vision-Flan-186K, while yielding a 73.7% reduction in wall-clock run time.

Click on the expansion arrows in each section to read the publication abstracts.

<<< Return to Current Research Outline