Follow
Aman Chadha
Aman Chadha
Other namesAman Rakesh Chadha, Aman R Chadha, A R Chadha
GenAI Leadership @ Apple • Stanford AI • UW-Madison ECE • Ex: AWS, Alexa, Nvidia, Qualcomm
Verified email at amazon.com - Homepage
Title
Cited by
Year
JEPA as a Neural Tokenizer: Learning Robust Speech Representations with Density Adaptive Attention
G Ioannides, C Constantinou, A Chadha, A Elkins, R Ziv, Y LeCun
NeurIPS 2025 UniReps Workshop, 2026
2026
The Reasoning Trap--Logical Reasoning as a Mechanistic Pathway to Situational Awareness
S Sahoo, A Chadha, V Jain, D Chaudhary
arXiv preprint arXiv:2603.09200, 2026
2026
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
S Sahoo, A Chadha, V Jain, D Chaudhary
ICLR 2026 Workshop on AI with Recursive Self-Improvement, 2026
2026
When Shallow Wins: Silent Failures and the Depth-Accuracy Paradox in Latent Reasoning
S Sahoo, A Chadha, V Jain, D Chaudhary
ICLR 2026 Workshop on Latent and Implicit Thinking, 2026
2026
POSITION: THE REASONING TRAP—LOGICAL REASONING AS A MECHANISTIC PATHWAY TO SITUATIONAL AWARENESS
S Sahoo, A Chadha, V Jain, D Chaudhary
ICLR 2026 Workshop on Logical Reasoning of Large Language Models, 2026
2026
Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
G Ioannides, A Kieback, J Goldfeder, L Pang, A Chadha, Y LeCun, R Ziv
arXiv preprint arXiv:2602.09040, 2026
2026
Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries
N Perez, S Bhaduri, A Chadha
arXiv preprint arXiv:2603.04413, 2026
2026
I Can't Believe It's Not Robust: Catastrophic Collapse of Safety Classifiers under Embedding Drift
S Sahoo, V Jain, D Chaudhary, A Chadha
ICLR 2026 "I Can't Believe It's Not Better" Workshop: Where Large Language …, 2026
2026
A Conversational Multi-agent AI Framework for Integrated Multi-omics Analysis and Biomedical Discovery
P Rajdeo, S Asanuma, M Kouril, P Lu, J Chen, A Chadha, S Prasath, ...
ICLR 2026 Workshop on Machine Learning for Genomics Explorations, 2026
2026
Neural FOXP2: Language Specific Neuron Steering for Targeted Language Improvement in LLMs
A Saha, T Joshi, V Jain, A Chadha, A Das
arXiv preprint arXiv:2602.00945, 2026
2026
RUDDER: Steering Prefetching in Distributed GNN Training using LLM Agents
A Sarkar, S Ghosh, N Tallent, A Chadha, T Roosta, A Jannesari
ICS 2026, 2026
2026
Assessing LLM Reliability on Temporally Recent Open-Domain Questions
P Krishnappa, A Das, V Jain, T Mukherjee, A Chadha
arXiv preprint arXiv:2602.11165, 2026
2026
SPINAL: Scaling-law and Preference Integration in Neural Alignment Layers
A Das, PP Saha, A Dhanda, V Jain, A Chadha, A Das
arXiv preprint arXiv:2601.06238, 2026
2026
ECLIPTICA: A Framework for Switchable LLM Alignment via Contrastive Instruction-Tuned Alignment (CITA)
K Wanaskar, G Jena, V Jain, A Chadha, A Das
arXiv preprint arXiv:2601.06157, 2026
2026
PECCAVI: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
S Dixit, A Aziz, S Bajpai, V Sharma, A Chadha, V Jain, A Das
CVPR 2026, 2026
2026
AlignMerge: Alignment-Preserving Large Language Model Merging via Fisher-Guided Geometric Constraints
A Roy, J Patel, A Chadha, V Jain, A Das
arXiv preprint arXiv:2512.16245, 2025
12025
Energy-Based Transformers are Scalable Learners and Thinkers
A Gladstone, G Nanduru, MM Islam, P Han, H Ha, A Chadha, Y Du, H Ji, ...
ICLR 2026, 2025
62025
Stochastic Chaos: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition
T Joshi, S Aggarwal, A Saha, A Pandey, S Dhoot, V Rai, R Goswami, ...
arXiv preprint arXiv:2601.07239, 2025
2025
SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correction
S Chaturvedi, A Chadha, L Bindschaedler
NeurIPS 2025 Deep Learning for Code Workshop, 2025
42025
Visual Counter Turing Test (VCT^2): Discovering the Challenges for AI-Generated Image Detection and Introducing Visual AI Index
N Imanpour, S Bajpai, S Ghosh, SR Sankepally, A Borah, HM Abdullah, ...
IJCNLP-AACL 2025 Main, 2025
12025
The system can't perform the operation now. Try again later.
Articles 1–20