12 papers
Extracting Work from Discrete Quantum Polytropic Processes
Vishal Anand, Swarup Kumar Giri, Avijit Misra +2
We establish an upper bound on extractable work for time-dependent, non-Markovian quantum heat engines operating with finite baths. This bound analytically isolates the distinct th…
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
Subhadip Mitra
Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAS…
Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs
Subhadip Mitra
Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with quality-diversity evolution (MAP-…
Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety
Subhadip Mitra
Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approa…
Constraint-Aware Execution Planning for Hybrid Space-Ground Compute Workloads
Subhadip Mitra
Low Earth orbit (LEO) satellites increasingly carry compute hardware capable of on-board processing, yet each satellite generates roughly two orders of magnitude more data than it…
Cross-Platform Fused MoE Dispatch in Triton: Portable Expert Routing Without CUDA
Subhadip Mitra
Mixture-of-Experts (MoE) architectures power the majority of frontier large language models, but their inference is bottlenecked by irregular memory access patterns and expert rout…