15 citations · 37 across the 31 of their papers we have counts for
33 papers
CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies
Santhosh GS, Ananya Ravi, Devika Jay +5
The deployment of Reinforcement Learning (RL) agents in critical domains must be preceded with a pipeline to evaluate the alignment of the RL agent with complex multi-objective spe…
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generation Evaluation
Anshul Bagaria, Sowmya S Sundaram, Gokul S Krishnan +1
LLM-as-a-Judge pipelines are increasingly used to evaluate AI-generated text, based on the assumption that judgments arise from reasoning over candidate responses with respect to a…
AI and Consumer Rights in India Working Paper
Omir Kumar, Sriya Sridhar, Vibhav Mithal +1
As AI systems proliferate in consumer facing applications, questions about liability for AI related harms remain unresolved. This working paper examines whether India's Consumer Pr…
KANEx: Translating Kolmogorov-Arnold Networks' Interpretability to Medical Explainability
Krithi Shailya, Ananya Lakshmi Ravi, Venkatanathan K. V. +4
Computer vision models have become highly effective for medical applications, yet their black-box nature continues to undermine clinician trust. In clinical workflows, chest X-ray…
Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability
Alicia Parrish, Rajat Shinde, Sanket Badhe +57
Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances,…
How Much Online RL is Enough? Informative Rollouts for Offline Preference Optimization in RLVR
Richa Verma, Balaraman Ravindran
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for reasoning in language models, with GRPO as its primary example. However, GRPO requires…
PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment
Richa Verma, Bavish Kulur, Sanjay Chawla +1
We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it from scratch. While costs cou…
International AI Safety Report 2026
Yoshua Bengio, Stephen Clare, Carina Prunkl +89
The International AI Safety Report 2026 synthesises the current scientific evidence on the capabilities, emerging risks, and safety of general-purpose AI systems. The report series…
OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories
Returaj Burnwal, Nirav Pravinbhai Bhatt, Balaraman Ravindran
This work addresses the problem of offline safe imitation learning (IL), where the goal is to learn safe and reward-maximizing policies from demonstrations that do not have per-tim…
Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
Jashaswimalya Acharjee, Balaraman Ravindran
We present Unified Latent Dynamics (ULD), a novel reinforcement learning algorithm that unifies the efficiency of model-free methods with the representational strengths of model-ba…
Know your Trajectory -- Trustworthy Reinforcement Learning deployment through Importance-Based Trajectory Analysis
Clifford F, Devika Jay, Abhishek Sarkar +4
As Reinforcement Learning (RL) agents are increasingly deployed in real-world applications, ensuring their behavior is transparent and trustworthy is paramount. A key component of…
International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management
Yoshua Bengio, Stephen Clare, Carina Prunkl +66
This second update to the 2025 International AI Safety Report assesses new developments in general-purpose AI risk management over the past year. It examines how researchers, publi…
SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression
Santhosh G S, Saurav Prakash, Balaraman Ravindran
Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression tec…
SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories
Returaj Burnwal, Nirav Pravinbhai Bhatt, Balaraman Ravindran
In this work, we study the problem of offline safe imitation learning (IL). In many real-world settings, online interactions can be risky, and accurately specifying the reward and…
International AI Safety Report 2025: First Key Update: Capabilities and Risk Implications
Yoshua Bengio, Stephen Clare, Carina Prunkl +70
Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to re…
IndiCASA: A Dataset and Bias Evaluation Framework in LLMs Using Contrastive Embedding Similarity in the Indian Context
Santhosh G S, Akshay Govind S, Gokul S Krishnan +2
Large Language Models (LLMs) have gained significant traction across critical domains owing to their impressive contextual understanding and generative capabilities. However, their…
Learning from Observation: A Survey of Recent Advances
Returaj Burnwal, Hriday Mehta, Nirav Pravinbhai Bhatt +1
Imitation Learning (IL) algorithms offer an efficient way to train an agent by mimicking an expert's behavior without requiring a reward function. IL algorithms often necessitate a…
AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs
Santhosh G S, Saurav Prakash, Balaraman Ravindran
The quadratic complexity of the attention mechanism remains a fundamental barrier to scaling Large Language Models (LLMs) to longer contexts, creating a critical bottleneck in both…
mFARM: Towards Multi-Faceted Fairness Assessment based on HARMs in Clinical Decision Support
Shreyash Adappanavar, Krithi Shailya, Gokul S Krishnan +2
The deployment of Large Language Models (LLMs) in high-stakes medical settings poses a critical AI alignment challenge, as models can inherit and amplify societal biases, leading t…
Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LMs for Academic Recommendations
Krithi Shailya, Akhilesh Kumar Mishra, Gokul S Krishnan +1
Large Language Models (LLMs) are increasingly used as daily recommendation systems for tasks like education planning, yet their recommendations risk perpetuating societal biases. T…
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Abhishek Verma, Nallarasan V, Balaraman Ravindran
Transfer learning in Reinforcement Learning (RL) enables agents to leverage knowledge from source tasks to accelerate learning in target tasks. While prior work, such as the Attend…
Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
Abhishek Verma, Nallarasan V, Balaraman Ravindran
Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critica…
LExT: Towards Evaluating Trustworthiness of Natural Language Explanations
Krithi Shailya, Shreya Rajpal, Gokul S Krishnan +1
As Large Language Models (LLMs) become increasingly integrated into high-stakes domains, there have been several approaches proposed toward generating natural language explanations…
International AI Safety Report
Yoshua Bengio, Sören Mindermann, Daniel Privitera +93
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…