16 papers
Localizing Safety Alignment: MLP Layers and Mid-Network Blocks Encode Refusal Behavior in Large Language Models
Mingyu Zong, Sampad Mohanty, Bhaskar Krishnamachari
Safety alignment in large language models is often treated as a distributed property of the entire network, yet its practical brittleness suggests that refusal behavior may be conc…
Closed-Loop Bayesian Bandit Encoder with GRAND Receiver for a Bursty Interference Channel
Bhaskar Krishnamachari
Interleaving mitigates burst errors but introduces decoding delay and removes temporal error structure that a channel-aware decoder could exploit. We consider packet-level selectio…
Who Restores the Peg? A Mean-Field Game Approach to Model Stablecoin Market Dynamics
Hardhik Mohanty, Bhaskar Krishnamachari
USDC and USDT are the dominant stablecoins pegged to $1 with a total market capitalization of over $300B and rising. Stablecoins make dollar value globally accessible with secure…
Proactive Market Making and Liquidity Analysis for Everlasting Options in DeFi Ecosystems
Hardhik Mohanty, Giovanni Zaarour, Bhaskar Krishnamachari
Everlasting options, a relatively new class of perpetual financial derivatives, have emerged to tackle the challenges of rolling contracts and liquidity fragmentation in decentrali…
A Survey on the Applications of Zero-Knowledge Proofs
Ryan Lavin, Xuekai Liu, Hardhik Mohanty +3
Zero-knowledge proofs (ZKPs) enable computational integrity and privacy by allowing one party to prove the truth of a statement without revealing underlying data. Compared with alt…
Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning
Diyi Hu, Bhaskar Krishnamachari
Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and existing value decomposition met…