51 papers
VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?
Mizanur Rahman, Arshia Azimlu, Shadikur Rahman +4
Vision-language models (VLMs) have shown strong capabilities in generating visualization code from textual or visual specifications. However, real-world visualization authoring is…
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub +3
Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as…
Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3
Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this gap by rescoring a model's ow…
Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models
Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3
This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel paral…
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Ye Liu, Srijan Bansal, Bo Pang +6
Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy fr…
The Illusion of Multi-Agent Advantage
Prathyusha Jwalapuram, Hehai Lin, Chuyuan Li +7
Prevailing wisdom posits that Multi-Agent Systems (MAS) are superior to Single-Agent Systems (SAS), citing advantages like context protection, parallel processing and distributed d…