Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Projector Is All You Train
Nyx Iskandar, Saathvik Selvan, Slater Victoroff
The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-sp…
cs.CL2026
Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility
Nyx Iskandar
This paper introduces tool efficiency, a new quantitative metric to evaluate the rate of useful tool calls in an LLM agent trajectory. To ensure that tool efficiency is well-define…
cs.CL2025
A Matter of Representation: Towards Graph-Based Abstract Code Generation
Nyx Iskandar, Hisham Bedri, Andy Tsen
Most large language models (LLMs) today excel at generating raw, sequential code with minimal abstractions and custom structures. However, there has been little work on graph-based…