Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Sai Srinivas Kancheti, Aditya Kanade, Vineeth N Balasubramanian, Tanuja Ganu
ACL 2026 | July 2026
Vineeth N Balasubramanian
Principal Researcher
出版物
-
-
-
Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian, Tanuja Ganu
2026 Annual Meeting of the Association for Computational Linguistics | July 2026
-
Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
S. V. Rebbapragada, Rishabh Lalla, Aveen Dayal, Tejal Kulkarni, A. Lalla, Vineeth N Balasubramanian, Muhammad Haris Khan
Computer Vision and Pattern Recognition | June 2026
-
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
Sarthak Mehrotra, S. V. Rebbapragada, Mani Hemanth Reddy Bonthu, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Source Models Leak What They Shouldn’t: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Understanding Task Transfer in Vision-Language Models
Bhuvan Sachdeva, Karan Uppal, Abhinav Java, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta, Vineeth N Balasubramanian, Deepti Ghadiyaram
May 2026
arXiv | May 2026
-
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu, Nagarajan Natarajan, Amit Sharma, Vineeth N Balasubramanian
International Conference on Learning Representations | May 2026
-
Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media
Megha Mariam K.M, Vineeth N Balasubramanian, C. V. Jawahar
CVPR 2026 | May 2026
-
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu
2026 COLM | April 2026
-
interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors
Vishak Bhat, Prateek Chanda, Ashmit Khandelwal, Maitreyi Swaroop, Vineeth N Balasubramanian, Subbarao Kambhampati, Nagarajan Natarajan, Amit Sharma
February 2026
-
-
-
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
Susmit Agrawal, Krishn Vishwas Kher, Swarnim Maheshwari, Saksham Mittal, Vineeth N Balasubramanian
NeurIPS 2025 | December 2025
-
Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
Pushkar Shukla, Aditya Chinchure, Emily Diana, Alexander Tolbert, Kartik Hosanagar, Vineeth N Balasubramanian, Leonid Sigal, Matthew Turk
EMNLP Findings | November 2025
-
Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
Hari Chandana Kuchibhotla, Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian
TMLR | May 2025, 巻2025
-
Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N Balasubramanian, Leonid Sigal
ACL | May 2025
-
Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
Aniket Vashishtha, Abbavaram Gowtham Reddy, Abhinav Kumar, Saketh Bachu, Vineeth N Balasubramanian, Amit Sharma
ICLR 2025 | April 2025
-
Teaching Transformers Causal Reasoning through Axiomatic Training
Aniket Vashishtha, Abhinav Kumar, Abbavaram Gowtham Reddy, Kabir Ahuja, Vineeth N Balasubramanian, Amit Sharma
ICLR 2025 - Workshop on Reasoning and Planning for LLMs | March 2025
-
-
-
Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian, Tanuja Ganu
2026 Annual Meeting of the Association for Computational Linguistics | July 2026
-
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
Sarthak Mehrotra, S. V. Rebbapragada, Mani Hemanth Reddy Bonthu, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Understanding Task Transfer in Vision-Language Models
Bhuvan Sachdeva, Karan Uppal, Abhinav Java, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
S. V. Rebbapragada, Rishabh Lalla, Aveen Dayal, Tejal Kulkarni, A. Lalla, Vineeth N Balasubramanian, Muhammad Haris Khan
Computer Vision and Pattern Recognition | June 2026
-
Source Models Leak What They Shouldn’t: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta, Vineeth N Balasubramanian, Deepti Ghadiyaram
May 2026
arXiv | May 2026
-
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu, Nagarajan Natarajan, Amit Sharma, Vineeth N Balasubramanian
International Conference on Learning Representations | May 2026
-
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu
2026 COLM | April 2026
-
interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors
Vishak Bhat, Prateek Chanda, Ashmit Khandelwal, Maitreyi Swaroop, Vineeth N Balasubramanian, Subbarao Kambhampati, Nagarajan Natarajan, Amit Sharma
February 2026
-
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
Susmit Agrawal, Krishn Vishwas Kher, Swarnim Maheshwari, Saksham Mittal, Vineeth N Balasubramanian
NeurIPS 2025 | December 2025
-
Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
Pushkar Shukla, Aditya Chinchure, Emily Diana, Alexander Tolbert, Kartik Hosanagar, Vineeth N Balasubramanian, Leonid Sigal, Matthew Turk
EMNLP Findings | November 2025
-
Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
Hari Chandana Kuchibhotla, Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian
TMLR | May 2025, 巻2025
-
Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N Balasubramanian, Leonid Sigal
ACL | May 2025
-
Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
Aniket Vashishtha, Abbavaram Gowtham Reddy, Abhinav Kumar, Saketh Bachu, Vineeth N Balasubramanian, Amit Sharma
ICLR 2025 | April 2025
-
Teaching Transformers Causal Reasoning through Axiomatic Training
Aniket Vashishtha, Abhinav Kumar, Abbavaram Gowtham Reddy, Kabir Ahuja, Vineeth N Balasubramanian, Amit Sharma
ICLR 2025 - Workshop on Reasoning and Planning for LLMs | March 2025
-
-
-
Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian, Tanuja Ganu
2026 Annual Meeting of the Association for Computational Linguistics | July 2026
-
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Sai Srinivas Kancheti, Aditya Kanade, Vineeth N Balasubramanian, Tanuja Ganu
ACL 2026 | July 2026
-
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
Sarthak Mehrotra, S. V. Rebbapragada, Mani Hemanth Reddy Bonthu, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Understanding Task Transfer in Vision-Language Models
Bhuvan Sachdeva, Karan Uppal, Abhinav Java, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
S. V. Rebbapragada, Rishabh Lalla, Aveen Dayal, Tejal Kulkarni, A. Lalla, Vineeth N Balasubramanian, Muhammad Haris Khan
Computer Vision and Pattern Recognition | June 2026
-
Source Models Leak What They Shouldn’t: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta, Vineeth N Balasubramanian, Deepti Ghadiyaram
May 2026
arXiv | May 2026
-
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu, Nagarajan Natarajan, Amit Sharma, Vineeth N Balasubramanian
International Conference on Learning Representations | May 2026
-
Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media
Megha Mariam K.M, Vineeth N Balasubramanian, C. V. Jawahar
CVPR 2026 | May 2026
-
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu
2026 COLM | April 2026
-
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
Susmit Agrawal, Krishn Vishwas Kher, Swarnim Maheshwari, Saksham Mittal, Vineeth N Balasubramanian
NeurIPS 2025 | December 2025
-
Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
Pushkar Shukla, Aditya Chinchure, Emily Diana, Alexander Tolbert, Kartik Hosanagar, Vineeth N Balasubramanian, Leonid Sigal, Matthew Turk
EMNLP Findings | November 2025
-
Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
Hari Chandana Kuchibhotla, Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian
TMLR | May 2025, 巻2025
-
Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N Balasubramanian, Leonid Sigal
ACL | May 2025
-
-
-
Source Models Leak What They Shouldn’t: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
-
-
Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
Hari Chandana Kuchibhotla, Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian
TMLR | May 2025, 巻2025
-
Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N Balasubramanian, Leonid Sigal
ACL | May 2025
-
-
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta, Vineeth N Balasubramanian, Deepti Ghadiyaram
May 2026
arXiv | May 2026
-
-
-
Mind’s Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian, Tanuja Ganu
2026 Annual Meeting of the Association for Computational Linguistics | July 2026
-
Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs
Sai Srinivas Kancheti, Aditya Kanade, Vineeth N Balasubramanian, Tanuja Ganu
ACL 2026 | July 2026
-
iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception
Sarthak Mehrotra, S. V. Rebbapragada, Mani Hemanth Reddy Bonthu, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Understanding Task Transfer in Vision-Language Models
Bhuvan Sachdeva, Karan Uppal, Abhinav Java, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
Foundation Model Priors Enhance Object Focus in Feature Space for Source-Free Object Detection
S. V. Rebbapragada, Rishabh Lalla, Aveen Dayal, Tejal Kulkarni, A. Lalla, Vineeth N Balasubramanian, Muhammad Haris Khan
Computer Vision and Pattern Recognition | June 2026
-
Source Models Leak What They Shouldn’t: Unlearning Zero-Shot Transfer in Domain Adaptation Through Adversarial Optimization
Arnav Devalapally, Poornima Jain, Kartik Srinivas, Vineeth N Balasubramanian
Computer Vision and Pattern Recognition | June 2026
-
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
Rohit Sinha, Kunal Tilaganji, Tanuja Ganu, Nagarajan Natarajan, Amit Sharma, Vineeth N Balasubramanian
International Conference on Learning Representations | May 2026
-
Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media
Megha Mariam K.M, Vineeth N Balasubramanian, C. V. Jawahar
CVPR 2026 | May 2026
-
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
Sai Srinivas Kancheti, Aditya Kanade, Rohit Sinha, Vineeth N Balasubramanian, Tanuja Ganu
2026 COLM | April 2026
-
Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks
Susmit Agrawal, Krishn Vishwas Kher, Swarnim Maheshwari, Saksham Mittal, Vineeth N Balasubramanian
NeurIPS 2025 | December 2025
-
Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models
Pushkar Shukla, Aditya Chinchure, Emily Diana, Alexander Tolbert, Kartik Hosanagar, Vineeth N Balasubramanian, Leonid Sigal, Matthew Turk
EMNLP Findings | November 2025
-
Response Wide Shut: Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N Balasubramanian, Leonid Sigal
ACL | May 2025
-
Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference
Aniket Vashishtha, Abbavaram Gowtham Reddy, Abhinav Kumar, Saketh Bachu, Vineeth N Balasubramanian, Amit Sharma
ICLR 2025 | April 2025
-
Teaching Transformers Causal Reasoning through Axiomatic Training
Aniket Vashishtha, Abhinav Kumar, Abbavaram Gowtham Reddy, Kabir Ahuja, Vineeth N Balasubramanian, Amit Sharma
ICLR 2025 - Workshop on Reasoning and Planning for LLMs | March 2025
-
-
-
interwhen: A Generalizable Framework for Verifiable Reasoning with Test-time Monitors
Vishak Bhat, Prateek Chanda, Ashmit Khandelwal, Maitreyi Swaroop, Vineeth N Balasubramanian, Subbarao Kambhampati, Nagarajan Natarajan, Amit Sharma
February 2026
-
-
-
Efficient Vocabulary-Free Fine-Grained Visual Recognition in the Age of Multimodal LLMs
Hari Chandana Kuchibhotla, Sai Srinivas Kancheti, Abbavaram Gowtham Reddy, Vineeth N Balasubramanian
TMLR | May 2025, 巻2025
-