Skip to content
conftrace_

Hiroki Furuta

14 papers · 2021–2026 · 5 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 ↓
+5 more ↓ 🌍 Conference Polyglot Β· Silver πŸ—ΊοΈ Taxonomy Completionist (33) πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🀝 Dynamic Duo (12)
πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ—ƒοΈ Keyword Collector (77) πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze

Venues

ICLR (6) ICML (4) NeurIPS (2) ACL (1) CVPR (1)

Top co-authors

Yutaka Matsuo (12) Shixiang Shane Gu (5) Yusuke Iwasawa (5) Aleksandra Faust (3) Tatsuya Matsushima (3) Ofir Nachum (3) Kuang-Huei Lee (3) Gouki Minegishi (3) Izzeddin Gur (3) Tadashi Kozuno (2)

Research topics

Artificial Intelligence (11) Core AI (10) Machine Learning (6) Deep Learning (4) Natural Language Processing (4) Reinforcement Learning (4) Methods (4) Application Areas (2) Applications (2) Architectures (2) Core Methods (2) Learning Paradigms (2) Learning Types Β· Deep Learning (2) Learning Types Β· Machine Learning (2) Optimization & Theory (2)

Keywords

large language model (5) deep reinforcement learning (2) offline reinforcement learning (2) multi-task learning (2) sparse autoencoder (2) reading comprehension (1) sample efficiency (1) representation learning (1) direct preference optimization (1) preference learning (1) policy learning (1) image editing (1) reinforcement learning (1) text-to-image generation (1) semantic representation (1) language model alignment (1) instruction following (1) reinforcement learning from human feedback (1) model alignment (1) imitation learning (1)

Papers

MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation CVPR 2026 Understanding Emergent Misalignment via Feature Superposition Geometry ACL 2026 Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence ICML 2025 Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks ICML 2025 Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words ICLR 2025 A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts ICML 2024 A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis ICLR 2024 Geometric-Averaged Preference Optimization for Soft Preference Labels NeurIPS 2024 Multimodal Web Navigation with Instruction-Finetuned Foundation Models ICLR 2024 A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation ICLR 2023 Generalized Decision Transformer for Offline Hindsight Information Matching ICLR 2022 Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning NeurIPS 2021 Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization ICLR 2021 Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning ICML 2021