From the 1 of 12 linked papers with an AI index.
12 papers
NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms
Shiyun Zhao, Xinwei Song, Tianyu Guo +7
The paper presents NormAct, a benchmark for evaluating whether embodied planners using multimodal large language models can infer and follow hidden social norms while completing ta…
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
Hengyu Fu, Tianyu Guo, Zixuan Wang +5
Large language models achieve strong performance on many reasoning tasks when allowed to externalize intermediate steps as Chain-of-Thought (CoT). However, many questions require t…
Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming
Qianfan Zhang, Tianyu Guo, Xuandi Ren +4
We study how to scale reasoning token budgets for competitive programming through two complementary approaches: training-time reinforcement learning (RL) and test-time parallel thi…
Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
Yixiao Huang, Hanlin Zhu, Tianyu Guo +5
Large language models (LLMs) can acquire new knowledge through fine-tuning, but this process exhibits a puzzling duality: models can generalize remarkably from new facts, yet are a…
TongSIM: A General Platform for Simulating Intelligent Machines
Zhe Sun, Kunlun Wu, Chuanjian Fu +24
As artificial intelligence (AI) rapidly advances, especially in multimodal large language models (MLLMs), research focus is shifting from single-modality text processing to the mor…
SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM Quantization
Tianyu Guo, Shanwei Zhao, Shiai Zhu +1
Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given th…