conftrace_

Takeshi Kojima

20 papers · 2021–2026 · 9 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🐝 Cross-Pollinator (12) 🌍 Conference Polyglot (9) 🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🏃 Academic Marathon (5)
🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (9) 🐣 Hot Topic Early Bird 🧬 Topic Evolution 🤝 Dynamic Duo (15) 🗃️ Keyword Collector (93) The Questioner Prolific Year (9) 💎 Century Club (15) 🔥 Unstoppable (5)

Conferences

ACL (4) EACL (4) EMNLP (4) IJCAI (2) NAACL (2) AACL (1) COLING (1) IJCNLP (1) NIPS (1)

Papers

Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths EACL 2026 Understanding Emergent Misalignment via Feature Superposition Geometry ACL 2026 ClinDet-Bench: Beyond Abstention, Evaluating Judgment Determinability of LLMs in Clinical Decision-Making ACL 2026 Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts EACL 2026 Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models EACL 2026 Slender-Mamba: Fully Quantized Mamba in 1.58 Bits From Head to Toe COLING 2025 Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar ACL 2025 Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning ACL 2025 Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge NAACL 2025 When Instructions Multiply: Measuring and Estimating LLM Capabilities of Multiple Instructions Following EMNLP 2025 Dynamic Injection of Entity Knowledge into Dense Retrievers EMNLP 2025 Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data AACL 2025 A Comprehensive Survey on Physical Risk Control in the Era of Foundation Model-enabled Robotics IJCAI 2025 Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data IJCNLP 2025 Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance? EMNLP 2024 On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons NAACL 2024 Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text EMNLP 2023 Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment IJCAI 2022 Large Language Models are Zero-Shot Reasoners NIPS 2022 Making Use of Latent Space in Language GANs for Generating Diverse Text without Pre-training EACL 2021