ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Souvik Kundu

Souvik Kundu

1

Affiliations

Affiliations

Intel Labs

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

13

papers

257

total citations

papers (13)

HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training With Crafted Input Noise

SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Fusing Models with Complementary Expertise

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation

NEURIPS 2025arXiv

OuroMamba: A Data-Free Quantization Framework for Vision Mamba

Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation

Don’t just prune by magnitude! Your mask topology is a secret weapon

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs ``Difficult" Downstream Tasks in LLMs

Vision HGNN: An Image is More than a Graph of Nodes

SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation