5 papers
The Script Tax: Measuring Tokenization-Driven Efficiency and Latency Disparities in Multilingual Language Models
Aradhya Dixit, Shreem Dixit
Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this scrip…
Project Aletheia: Verifier-Guided Distillation of Backtracking for Small Language Models
Aradhya Dixit, Tianxi Liang, Jai Telang
Small Language Models (SLMs, under 10B parameters) are attractive for private, on-device deployment, yet they frequently fail on strict constraint-satisfaction problems due to line…
Evaluating Self-Correcting Vision Agents Through Quantitative and Qualitative Metrics
Aradhya Dixit
Recent progress in multimodal foundation models has enabled Vision-Language Agents (VLAs) to decompose complex visual tasks into executable tool-based plans. While recent benchmark…
PCN-Rec: Agentic Proof-Carrying Negotiation for Reliable Governance-Constrained Recommendation
Aradhya Dixit, Shreem Dixit
Modern LLM-based recommenders can generate compelling ranked lists, but they struggle to reliably satisfy governance constraints such as minimum long-tail exposure or diversity req…
Semantic Event Graphs for Long-Form Video Question Answering
Aradhya Dixit, Tianxi Liang
Long-form video question answering remains challenging for modern vision-language models, which struggle to reason over hour-scale footage without exceeding practical token and com…