Rahul Kumar

Giansalvo Cirrincione, Rahul Ranjeev Kumar

DDCL-Attention is a prototype-based readout layer for transformer encoders that replaces simple pooling methods, such as mean pooling or class tokens, with a learned compression mechanism. It uses a small set of global prototype vectors and assigns tokens to them through soft probabilistic matching, producing compact token summaries at linear complexity in sequence length. The method offers three main advantages. First, it avoids prototype collapse through an exact decomposition of the training loss into a reconstruction term and a diversity term, ensuring that prototypes remain distinct. Second, its joint training with the encoder is shown to be stable under a practical timescale condition, using Tikhonov's singular perturbation theory and explicit learning-rate constraints. Third, the same framework supports three uses: a final readout layer, a differentiable codebook extending VQ-VAE, and a hierarchical document compressor. Experiments on four datasets confirm the theoretical predictions: the loss decomposition holds exactly, prototype separation grows as expected when the stability condition is met, and the codebook reaches full utilization, outperforming standard hard vector quantization. An additional study on orbital debris classification shows that the method also applies beyond standard NLP and vision tasks, including scientific tabular data.

Rajat Kumar Jenamani, Rahul Kumar, Parth Mall et al.

Sampling based methods are widely used for robotic motion planning. Traditionally, these samples are drawn from probabilistic ( or deterministic ) distributions to cover the state space uniformly. Despite being probabilistically complete, they fail to find a feasible path in a reasonable amount of time in constrained environments where it is essential to go through narrow passages (bottleneck regions). Current state of the art techniques train a learning model (learner) to predict samples selectively on these bottleneck regions. However, these algorithms depend completely on samples generated by this learner to navigate through the bottleneck regions. As the complexity of the planning problem increases, the amount of data and time required to make this learner robust to fine variations in the structure of the workspace becomes computationally intractable. In this work, we present (1) an efficient and robust method to use a learner to locate the bottleneck regions and (2) two algorithms that use local sampling methods to leverage the location of these bottleneck regions for efficient motion planning while maintaining probabilistic completeness. We test our algorithms on 2 dimensional planning problems and 7 dimensional robotic arm planning, and report significant gains over heuristics as well as learned baselines.