1 citations · 1 across the 3 of their papers we have counts for
6 papers
Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability
Davide Wiest, Ahanaf Hasan Ariq, Abdul Monaf Chowdhury
Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance s…
Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?
Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque +2
Goal-conditioned reinforcement learning (GCRL) relies heavily on how target goals are represented to the policy. While recent methods encode goals via temporal distance, occupancy,…
GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences
Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman +1
In offline goal-conditioned reinforcement learning (GCRL), divide-and-conquer scales to long horizons by joining two shorter segments at a subgoal. However, under stochastic dynami…
Counting Through Occlusion: Framework for Open World Amodal Counting
Safaeid Hossain Arib, Rabeya Akter, Abdul Monaf Chowdhury +2
Object counting has achieved remarkable success on visible instances, yet state-of-the-art (SOTA) methods fail under occlusion. This failure stems from a fundamental architectural…
LaGEA: Language Guided Embodied Agents for Robotic Manipulation
Abdul Monaf Chowdhury, Akm Moshiur Rahman Mazumder, Safaeid Hossain Arib +1
Robotic manipulation benefits from foundation models that describe goals, but today's agents still lack a principled way to learn from their own mistakes. We ask whether natural la…
T3Time: Tri-Modal Time Series Forecasting via Adaptive Multi-Head Alignment and Residual Fusion
Abdul Monaf Chowdhury, Rabeya Akter, Safaeid Hossain Arib
Multivariate time series forecasting (MTSF) seeks to model temporal dynamics among variables to predict future trends. Transformer-based models and large language models (LLMs) hav…