9 papers · 1 filter
LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis
Faruk Alpay, Bugra Kilictas
Structured sequence generation often requires a model to satisfy several input-derived constraints in a single output. Standard decoding methods may assign high probability to flue…
Attention Meets Reachability: Structural Equivalence and Efficiency in Grammar-Constrained LLM Decoding
Faruk Alpay, Bilge Senturk
We study grammar-constrained decoding (GCD) as a coupling between an autoregressive next-token distribution and a reachability oracle over a pushdown system compiled from a context…
Asymptotic Semantic Collapse in Hierarchical Optimization
Faruk Alpay, Bugra Kilictas
Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics, yielding near-uniform behavior across agents. We…
Bare-Metal Tensor Virtualization: Overcoming the Memory Wall in Edge-AI Inference on ARM64
Bugra Kilictas, Faruk Alpay
The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the "Memory Wall" the bottleneck where data movement latency outstrips arithmetic thr…
Rate-Distortion Analysis of Compressed Query Delegation with Low-Rank Riemannian Updates
Faruk Alpay, Bugra Kilictas
Bounded-context agents fail when intermediate reasoning exceeds an effective working-memory budget. We study compressed query delegation (CQD): (i) compress a high-dimensional late…
Manipulating Transformer-Based Models: Controllability, Steerability, and Robust Interventions
Faruk Alpay, Taylan Alpay
Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principl…