Anurag Koul

5 papers · 2018–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

ICML (3) ACL (1) ICLR (1)

Top co-authors

Alan Fern (3) Shaoru Chen (1) Samuel Greydanus (1) Ben Evans (1) Yu Yu (1) Miroslav Dudı́k (1) Yonathan Efroni (1) Yawen Wu (1) Mohamad H Danesh (1) Lili Wu (1)

Research topics

Artificial Intelligence (4) Machine Learning (4) Core AI (4) Reinforcement Learning (3) Core Methods (3) Deep Learning (2) Applications (2) Architectures (2) Learning Types (2) Robotics (1) Capabilities (1) Methods (1)

Keywords

policy network (2) atari game (2) recurrent neural network (2) code completion (1) attention mechanism (1) visual explanation (1) inverse dynamics (1) saliency map (1) sampling efficiency (1) goal-conditioned policy (1) retrieval-augmented generation (1) latent state (1) latency optimization (1) finite state machine (1) policy interpretation (1) large language model (1) finite-state representation (1) atari agent (1) speculative retrieval (1) quantized bottleneck insertion (1)

Papers

SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion ACL 2026 PcLast: Discovering Plannable Continuous Latent States ICML 2024 Re-understanding Finite-State Representations of Recurrent Policy Networks ICML 2021 Learning Finite State Representations of Recurrent Policy Networks ICLR 2019 Visualizing and Understanding Atari Agents ICML 2018