Get started
Author

Amit Dhanda

Observed name: Dhanda, Amit
Observed institution: Amazon (United States)
OpenAlex ID: A5043887050
Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
2026 · Karmakar, Agnibh, Parvatikar, Mayur, et al. · arXiv (Cornell University)
PDF
MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
2026 · Saha, Partha Pratim, Raina, Samarth, et al. · arXiv (Cornell University)
PDF
Safe Equilibrium Policy Optimization for Strategic Agent Policies
2026 · Arumugam, Karthika, Manku, Kiran Kumar, et al. · arXiv (Cornell University)
PDF
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
2026 · Chauhan, Anay, Kumar, Gurucharan Marthi Krishna, et al. · arXiv (Cornell University)
PDF
DeltaLogic: Minimal Premise Edits Reveal Belief-Revision Failures in Logical Reasoning Models
2026 · Dhanda, Amit · arXiv (Cornell University)
PDF
Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models
2026 · Bai, Yunfei, Dhanda, Amit, et al. · arXiv (Cornell University)
PDF
SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers
2026 · Das, Arion, Saha, Partha Pratim, et al. · arXiv (Cornell University)
PDF
D-STEER: Two-Way Control of DPO-Induced Safety Behavior in Activation Space
2025 · Raina, Samarth, Aggarwal, Saksham, et al. · arXiv (Cornell University)
PDF
Works count: 8
Citation count:
H-index:
I10-index:
Year
Topic
Type