21 citations · 33 across the 16 of their papers we have counts for
17 papers
Reward-Gated On-Policy Distillation
Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3
On-policy distillation is a powerful way to transfer reasoning ability from a strong teacher to a smaller student: the student samples trajectories from its own policy, and the tea…
NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
Konstantinos Kontras, Trui Osselaer, Stylianos G. Mouslech +12
Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG),…
SCATR: Simple Calibrated Test-Time Ranking
Divya Shyamal, Marta Knežević, Lan Tran +3
Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: gener…
Interleaved Head Attention
Sai Surya Duvvuri, Chanakya Ekbote, Rachit Bansal +6
Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H…
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
Keane Ong, Sabri Boughorbel, Luwei Xiao +9
Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts. However, behavioral data is inherently heterogeneous, compr…
MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
Chanakya Ekbote, Vijay Lingam, Sujay Sanghavi +4
Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relative Policy Optimization (GRPO) emergin…
What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains
Chanakya Ekbote, Marco Bondaschi, Nived Rajaraman +4
In-context learning (ICL) is a hallmark capability of transformers, through which trained models learn to adapt to new tasks by leveraging information from the input context. Prior…
PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts
Hengzhi Li, Justin Zhang, Brendon Jiang +9
Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear ins…
QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Training
Wei Dai, Peilin Chen, Chanakya Ekbote +1
Clinical decision-making routinely demands reasoning over heterogeneous data, yet existing multimodal language models (MLLMs) remain largely vision-centric and fail to generalize a…
TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models
Jaewoo Lee, Keyang Xuan, Chanakya Ekbote +3
Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased mo…
Understanding the Emergence of Multimodal Representation Alignment
Megan Tjandrasuwita, Chanakya Ekbote, Liu Ziyin +1
Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly…
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
Ashok Vardhan Makkuva, Marco Bondaschi, Chanakya Ekbote +4
In recent years, transformer-based models have revolutionized deep learning, particularly in sequence modeling. To better understand this phenomenon, there is a growing interest in…
FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
Chanakya Ekbote, Ajinkya Pankaj Deshpande, Arun Iyer +2
Unsupervised node representations learnt using contrastive learning-based methods have shown good performance on downstream tasks. However, these methods rely on augmentations that…
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
Chanakya Ekbote, Moksh Jain, Payel Das +1
Generative Flow Networks (GFlowNets) have demonstrated significant performance improvements for generating diverse discrete objects given a reward function , indicating t…
Biological Sequence Design with GFlowNets
Moksh Jain, Emmanuel Bengio, Alex-Hernandez Garcia +10
Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive…
A Piece-wise Polynomial Filtering Approach for Graph Neural Networks
Vijay Lingam, Chanakya Ekbote, Manan Sharma +3
Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform…
A Stochastic Game Framework for Efficient Energy Management in Microgrid Networks
Shravan Nayak, Chanakya Ajit Ekbote, Annanya Pratap Singh Chauhan +5
We consider the problem of energy management in microgrid networks. A microgrid is capable of generating a limited amount of energy from a renewable resource and is responsible for…