Ego2World is introduced, an executable benchmark that turns egocentric cooking videos into executable symbolic worlds governed by graph-transition rules and shows that persistent belief memory improves task completion while reducing repeated visual exploration, suggesting that belief maintenance should be a first-class...
Qin-Chuan Cheng, Zhan Gong, Peng-Zhan Sun et al.· arXiv.org· 1 citation
Knowledge Graph Question Answering (KGQA) aims to answer user questions by reasoning over Knowledge Graphs (KGs). Recent methods use supervision derived from answer labels or refined by Large Language Models (LLMs) to train models that retrieve KG evidence for LLM-based answer reasoning. However, answer-derived supervi...
Shengxiang Gao, Chao Lei, Jey Han Lau et al.· 0 citations
Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. However, such models are fundamentally limited by exposure bias: during inference, errors can accumulate across sequential predictions, leading to pronounced quality degradati...
Wei Li, Shibo Feng, Pengcheng Wu et al.· 0 citations
Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents. So, we need to quickly find a new safe plan. Replanning only the delayed agent often does not yield an efficient plan, and sometimes cannot even yield a feasible one. On the other hand,...
Issa Hanou, Eric Kemmeren, Devin Wild Thomas et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Molecule generation from extremely limited training data is a key challenge in drug discovery. Existing fragment-based methods are more suitable than atom-based approaches in this regime, but typically optimize fragment selection separately from downstream generation. Expert feedback is also especially valuable with li...
Yuto Suzuki, Paul Awolade, Daniel V. LaBarbera et al.· 0 citations
Three novel creative-reasoning tasks requiring concrete solutions in low-constraint settings are introduced, suggesting distinct performance patterns across task structures: T-UoT is strongest in low-constraint, high-specificity settings, E-UoT in more constrained, high-specificity settings, and C-UoT in low-constraint...
Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their effectiveness remains constrained when reasoning extends beyond the knowledge acquired during pretraining. Conventional approaches, such as fine-tuning or retrieval-augmente...
Zerui Yang, Yuwei Wan, Siyu Yan et al.· 0 citations
Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from random noise, which can lead to unstable interaction prediction. We introduce 4D-HOF, a feed-forward framework that reconstructs 4D hand-object interactio...
Shi-Qi Li, Sean Cho, Yi-Jie Li et al.· 0 citations
This work introduces a calibration pipeline that combines learned stereo depth with a joint factor graph, pooling all episodes collected from the same physical robot to recover its shared kinematic parameters alongside per-scene extrinsics, and trains DepthWorld, a Stable Video Diffusion-based world model that jointly...
Jai Bardhan, Josef Sivic, Vladimír Petrík· 1 citation
WorldSonus, an interactive video-to-audio framework designed for real-time spatial sound synthesis in world models, generalizes effectively to open-domain video-to-audio benchmarks, matching or outperforming state-of-the-art bidirectional models in both acoustic quality and spatial alignment.
Peng Fang, Jing-Yi Fa, Kam-Man Wu et al.· 0 citations
Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory target for control. Our key insight is that, although low-level actions are embodiment-specific, their underlying motion intent can capture task-relevan...
Li-Han Zha, Shresth Grover, Tenny Yin et al.· 0 citations
Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when t...
Su-Xin Ji, Hung-Tao Wan, Shao-Xuan Chen et al.· 0 citations
