Aashiq Muhamed
10 papers · 2021–2026 · 6 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (20) 🐣 Hot Topic Early Bird
💎
Century Club · Bronze
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI
(8)
Deep Learning
(4)
Machine Learning
(3)
Architectures
(3)
Natural Language Processing
(2)
Application Areas
(2)
Learning Paradigms
(2)
Models
(2)
Applications
(1)
Learning Types
(1)
Optimization & Theory · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Resources & Methods
(1)
Understanding
(1)
Keywords
knowledge base
(2)
retrieval-augmented generation
(2)
sparse autoencoder
(2)
knowledge distillation
(1)
question answering
(1)
text generation
(1)
generative evaluation
(1)
text-to-image generation
(1)
feature disentanglement
(1)
collaborative learning
(1)
semantic similarity
(1)
implicit neural representation
(1)
autoregressive model
(1)
language model
(1)
foundation model
(1)
low-rank adaptation
(1)
generative adversarial network
(1)
mechanistic interpretability
(1)
pre-trained language model
(1)
concept discovery
(1)
Papers
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs’ Cultural Processing of Figurative Language
EACL 2026
Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders
ACL 2026
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
EACL 2026
CoRAG: Collaborative Retrieval-Augmented Generation
NAACL 2025
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
NAACL 2025
Adversarial Text to Continuous Image Generation
CVPR 2024
GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
EMNLP 2024
Less is Fed More: Sparsity Reduces Feature Distortion in Federated Learning
EMNLP 2024
ReAugKD: Retrieval-Augmented Knowledge Distillation For Pre-trained Language Models
ACL 2023
Symbolic Music Generation with Transformer-GANs
AAAI 2021