Author

Amitava Das

Observed name: Das, Amitava

Institutions: University of Dhaka, Birla Institute of Technology and Science, Pilani - Goa Campus, Birla Institute of Technology and Science, Pilani

Observed institutions: University of Dhaka, Birla Institute of Technology and Science, Pilani - Goa Campus, Birla Institute of Technology and Science, Pilani

OpenAlex ID: A5122945669

Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition

2026 · Joshi, Tanmay, Aggarwal, Shourya, et al. · arXiv (Cornell University) · 1

Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time

2026 · Karmakar, Agnibh, Parvatikar, Mayur, et al. · arXiv (Cornell University)

GuardPaint:SpeculativeSafetyDecodingforText-to-ImageGeneration

2026 · Dhoot, Shreyash, Dhiman, Paras, et al. · arXiv (Cornell University)

FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds

2026 · Wanaskar, Kapil, Jena, Gaytri, et al. · arXiv (Cornell University)

MAAT: Multi-phase Adapter-Aware Targeted Unlearning

2026 · Yagnik, Suryash, Gaur, Shubham, et al. · arXiv (Cornell University)

Findings of the Counter Turing Test: AI-Generated Text Detection

2026 · Roy, Rajarshi, Singh, Gurpreet, et al. · arXiv (Cornell University)

Findings of the Counter Turing Test: AI-Generated Image Detection

2026 · Roy, Rajarshi, Imanpour, Nasrin, et al. · arXiv (Cornell University)

SleepWalk: A Three-Tier Benchmark for Stress-Testing Instruction-Guided Vision-Language Navigation

2026 · Rawal, Niyati, Ravva, Sushant, et al. · arXiv (Cornell University)

CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation

2026 · Sinha, Aarush, Das, Arion, et al. · arXiv (Cornell University)

SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers

2026 · Das, Arion, Saha, Partha Pratim, et al. · arXiv (Cornell University)

ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment

2026 · Wanaskar, Kapil, Jena, Gaytri, et al. · arXiv (Cornell University)

A Comprehensive Dataset for Human vs. AI Generated Image Detection

2026 · Roy, Rajarshi, Aziz, Ashhar, et al. · arXiv (Cornell University)

GRIT -- Geometry-Aware PEFT with K-FACPreconditioning, Fisher-Guided Reprojection, andDynamic Rank Adaptation

2026 · Saha, Pritish, Rajbangshi, Chandrav, et al. · arXiv (Cornell University)

Works count: 13

Citation count: 1

H-index: 1

I10-index: