collaborators

7 papers

cs.DC2026

Agentic AI Workload Characteristics

Yichao Yuan, Ankita Nayak, Souvik Kundu +1

Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time.…

cs.CL2026

One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness

Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu +1

Instruction-tuned large language models produce helpful, structured responses, but how robust is this helpfulness under trivial constraints? We show that simple lexical constraints…

cs.AI2026

SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models

Jiayi Tian, Seyedarmin Azizi, Yequan Zhao +7

Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both…

cs.AI2026

RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning

Jiayi Tian, Yupeng Su, Ryan Solgi +2

Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference la…

cs.LG2026

Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration

Jucheng Shen, Gaurav Sarkar, Yeonju Ro +4

We present CadLLM, a training-free method to accelerate the inference throughput of diffusion-based LLMs (dLLMs). We first investigate the dynamic nature of token unmasking confide…

stat.ML2026

Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning

Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi +2

Many recent reasoning gains in large language models can be explained as distribution sharpening: biasing generation toward high-likelihood trajectories already supported by the pr…