19 citations · 36 across the 42 of their papers we have counts for
43 papers
Merge++: Universal Merge Refinement Through Data-Free Checkpoint Inversion
Aditya Pola, Vineeth N. Balasubramanian
Model merging consolidates fine-tuned experts into one multi-task model without retraining. All existing data-free methods approach this problem entirely in weight space. Restricte…
ISA-Bench: A Benchmark for Computational Reasoning Across Instruction Set Architectures
Aditya Pola, Arkaprava Majumdar, Vineeth N. Balasubramanian
Large language model code generation benchmarks primarily evaluate well-resourced languages like Python and Java, where models benefit from abundant training data. They provide lim…
Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement
Uma Ranjan, Kunal Tilaganji, Aditya Koul +9
Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models to abstain when uncertain im…
VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu +3
Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations.…
Real-Time Source-Free Object Detection
Sairam VCR, Varun Gopal, Poornima Jain +2
Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints, yet existing source-free object detec…
Formal Concept Lattices are Good Semantic Scaffolds for Concept-Based Learning
Deepika SN Vemuri, Sayanta Adhikari, Ankit Saha +2
Learning semantics is essential for deep learning models to be interpretable and better aligned with human reasoning. Concept-based models approach this by representing classes thr…
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal +3
While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted ev…
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu +3
Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable limitations.…
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Sai Srinivas Kancheti, Aditya Sanjiv Kanade, Vineeth N. Balasubramanian +1
Multimodal Reasoning Models (MRMs) leveraging Chain-of-Thought (CoT) based thinking have revolutionized mathematical and logical problem-solving. However, we show that this paradig…
Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti +2
Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains…
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha +2
Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks. However, we observe tha…
Source Models Leak What They Shouldn't : Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas +1
The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may inadvertently retain and lea…
interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time Verification
Vishak K Bhat, Prateek Chanda, Vijval Ekbote +6
Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctness. Existing approaches either verify o…
Source-Free Domain Adaptation by Optimizing Batch-Wise Cosine Similarity
Harsharaj Pathak, Vineeth N Balasubramanian
Source-Free Domain Adaptation (SFDA) is an emerging area of research that aims to adapt a model trained on a labeled source domain to an unlabeled target domain without accessing t…
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
Sarthak Mehrotra, Sairam V C Rebbapragada, Mani Hemanth Reddy Bonthu +1
Multimodal Large Language Models (MLLMs) show strong potential for interpreting and interacting with complex, pixel-rich Graphical User Interface (GUI) environments. However, build…
LogicCBMs: Logic-Enhanced Concept-Based Learning
Deepika SN Vemuri, Gautham Bellamkonda, Aditya Pola +1
Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpreta…
Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
Sairam VCR, Rishabh Lalla, Aveen Dayal +4
Current state-of-the-art approaches in Source-Free Object Detection (SFOD) typically rely on Mean-Teacher self-labeling. However, domain shift often reduces the detector's ability…
Annotation-Free Class-Incremental Learning
Hari Chandana Kuchibhotla, K S Ananth, Vineeth N Balasubramanian
Despite significant progress in continual learning ranging from architectural novelty to clever strategies for mitigating catastrophic forgetting most existing methods rest on a st…
Where does an LLM begin computing an instruction?
Aditya Pola, Vineeth N. Balasubramanian
Following an instruction involves distinct sub-processes, such as reading content, reading the instruction, executing it, and producing an answer. We ask where, along the layer sta…
Understanding Task Transfer in Vision-Language Models
Bhuvan Sachdeva, Karan Uppal, Abhinav Java +1
Vision-Language Models (VLMs) perform well on multimodal benchmarks but lag behind humans and specialized models on visual perception tasks like depth estimation or object counting…
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz +2
Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable,…
Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
Pushkar Shukla, Aditya Chinchure, Emily Diana +5
The biases exhibited by text-to-image (TTI) models are often treated as independent, though in reality, they may be deeply interrelated. Addressing bias along one dimension - such…
Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
Hari Chandana Kuchibhotla, Sai Srinivas Kancheti, Abbavaram Gowtham Reddy +1
Fine-grained Visual Recognition (FGVR) involves distinguishing between visually similar categories, which is inherently challenging due to subtle inter-class differences and the ne…
POET: Prompt Offset Tuning for Continual Human Action Adaptation
Prachi Garg, Joseph K J, Vineeth N Balasubramanian +6
As extended reality (XR) is redefining how users interact with computing devices, research in human action recognition is gaining prominence. Typically, models deployed on immersiv…