9 papers
SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering
Ayush Dwivedi, Qixin Wang, Ashvi Soni +5
Vision-language models (VLMs) are powerful for chart question answering, but invoking a VLM for every query can be unnecessarily expensive when many questions are answerable from O…
Eureka: Intelligent Feature Engineering for Enterprise AI Cloud Resource Demand Prediction
Hangxuan Li, Renjun Jia, Xuezhang Wu +3
Effective features are crucial for predictive model performance, but creating them often requires domain expertise, limiting scalability across applications. We define feature engi…
Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation
Tianlei Chen, Jiao Ou, Ziyuan Liu +3
Domain specialization can improve LLM behavior, but often weakens the general capabilities inherited from the original model. Recent Multi-Teacher On-Policy Distillation (MOPD) pip…
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
Zhaoyang Chu, Jiarui Hu, Xingyu Jiang +8
We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 ter…
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Minxuan Lv, Tiehua Mei, Tanlong Du +9
We present GoLongRL, a fully open-source, capability-oriented post-training recipe for long-context reinforcement learning with verifiable rewards (RLVR). Existing long-context RL…
SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents
Han Li, Vibhor Malik, Zahra Zanjani Foumani +17
A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistical significance, and risks de…
DADF: A Distribution-Aware Debiasing Framework for Watch-Time Regression in Recommender Systems
Yiqing Yang, Xinlong Zhao, Zhao Liu +4
Watch-time predictors in short-video recommender systems can be approximately calibrated by their own scores while still overestimating short observations and underestimating long…
A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science
Zonglin Yang, Runze Mao, Tianhao Wu +3
To advance foundation Large Language Models (LLMs) for combustion science, this study presents the first end-to-end framework for developing domain-specialized models for the combu…
AdaptJobRec: Enhancing Conversational Career Recommendation through an LLM-Powered Agentic System
Qixin Wang, Dawei Wang, Kun Chen +11
In recent years, recommendation systems have evolved from providing a single list of recommendations to offering a comprehensive suite of topic focused services. To better accompli…