Peter Anthony Beerel

5 papers · 2023–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) ❓ The Questioner

Venues

ICLR (3) EMNLP (2)

Top co-authors

Souvik Kundu (3) Gourav Datta (3) Zeyu Liu (3) Anni Li (2) Yuke Zhang (1) Shunlin Lu (1) Sreetama Sarkar (1) Srikanth Ronanki (1) Sravan Babu Bodapati (1) Yue Che (1)

Research topics

Deep Learning (5) Machine Learning (3) Architectures (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Optimization & Theory · Machine Learning (2) Optimization & Theory · Deep Learning (2) Speech & Audio (1) Learning Types (1) Recognition (1) Techniques (1)

Keywords

efficient computing (2) spiking neural network (2) model compression (2) speech recognition (1) efficient inference (1) neural network optimization (1) sequence learning (1) image recognition (1) vision-language model (1) hallucination mitigation (1) inference optimization (1) attention head (1) hallucination reduction (1) multimodal understanding (1) transformer optimization (1) linear attention (1) binary neural network (1) rectified linear unit (1) long-context modeling (1) inference-time intervention (1)

Papers

LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling EMNLP 2025 Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression EMNLP 2025 Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision? ICLR 2024 LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units ICLR 2024 Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference ICLR 2023