papers

Publications (10)

cs.LG2025

Compressing Many-Shots in In-Context Learning

Devvrit Khatri, Pranamya Kulkarni, Nilesh Gupta +9

Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Conte…

cs.CL2025

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…

cs.CL2025

Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning

Kai Zhang, Congchao Wang, Liqian Peng +2

Large Language Models (LLMs) have gained significant attention in on-device applications due to their remarkable performance across real-world tasks. However, on-device LLMs often…

cs.CL2024

Cascade-Aware Training of Language Models

Congchao Wang, Sean Augenstein, Keith Rush +5

Reducing serving cost and latency is a fundamental concern for the deployment of language models (LMs) in business applications. To address this, cascades of LMs offer an effective…

cs.CL2025

Universal Model Routing for Efficient LLM Inference

Wittawat Jitkrittum, Harikrishna Narasimhan, Ankit Singh Rawat +9

Model routing is a simple technique for reducing the inference cost of large language models (LLMs), wherein one maintains a pool of candidate LLMs, and learns to route each prompt…

cs.CV2021

Multi-path Neural Networks for On-device Multi-domain Visual Classification

Qifei Wang, Junjie Ke, Joshua Greaves +9

Learning multiple domains/tasks with a single model is important for improving data efficiency and lowering inference cost for numerous vision tasks, especially on resource-constra…

cs.CL2026

Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens

Wei-Lin Chen, Liqian Peng, Tian Tan +5

Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that…

cs.CV2025

What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models

Abdelrahman Abdelhamed, Mahmoud Afifi, Alec Go

Large language models (LLMs) have been effectively used for many computer vision tasks, including image classification. In this paper, we present a simple yet effective approach fo…

cs.CV2018

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications

Tien-Ju Yang, Andrew Howard, Bo Chen +5

This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algo…

cs.CL2026

Gemma 4 Technical Report

Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320

We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…