2 citations · 2 across the 13 of their papers we have counts for
8 papers · 1 filter
MindCraft: How Concept Trees Take Shape In Deep Models
Bowei Tian, Yexiao He, Wanghao Ye +3
Large-scale foundation models demonstrate strong performance across language, vision, and reasoning tasks. However, how they internally structure and stabilize concepts remains elu…
Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
Qinyan Zhang, Xinping Lei, Ruijie Miao +18
Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized…
Benchmarking the Pedagogical Knowledge of Large Language Models
Maxime Lelièvre, Amy Waldock, Meng Liu +7
Benchmarks like Massive Multitask Language Understanding (MMLU) have played a pivotal role in evaluating AI's knowledge and abilities across diverse domains. However, existing benc…
Spectral Principal Paths: A Spectral Perspective on Linear Representation Formation in LLMs
Bowei Tian, Xuntao Lyu, Meng Liu +2
High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circuits to structured semantic direc…
CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
Wanghao Ye, Sihan Chen, Yiting Wang +18
Current large language model (LLM) agents lack authentic human psychological processes necessary for genuine digital twins and social AI applications. To address this limitation, w…
CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs
Guoheng Sun, Ziyao Wang, Bowei Tian +7
As post-training techniques evolve, large language models (LLMs) are increasingly augmented with structured multi-step reasoning abilities, often optimized through reinforcement le…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
Why Representation Engineering Works: A Theoretical and Empirical Study in Vision-Language Models
Bowei Tian, Xuntao Lyu, Meng Liu +2
Representation Engineering (RepE) has emerged as a powerful paradigm for enhancing AI transparency by focusing on high-level representations rather than individual neurons or circu…