Zero-shot vision-and-language navigation (VLN) requires an agent to use past observations without navigation-specific training. We study what information an 8B-scale navigation system should retain and how it should be organized for subsequent decisions. Our agent combines instruction progress, hierarchically compresse...
Yuhang Peng, Zhikai Wang, Ziyi Wang et al.· 0 citations
AI compute is becoming large and fast-changing electrical loads. Its impacts on data center infrastructure and power grids depend not only on total energy consumption, but also on how their power draw moves over sub-second to minute timescales, including peaks, ramps, and synchronized fluctuations across accelerators....
Jian-Sheng Wang, Jaskeerat Singh, Hao Xu et al.· 0 citations
Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce EPSBench, a benchmark for studying this ability across 149 firm-quarters from 86 US companies. Agents read a fixed collection of filings, earnings-ca...
Yanbin Yin, Chuyu Xu, Liqin Ye et al.· 0 citations
Time-series forecasters are ranked almost entirely by accuracy metrics, but a forecast's decision value, its effect on the downstream decision, need not track accuracy and is rarely measured. This problem compounds as large language model (LLM) agents increasingly consume forecasters as tools, mediating them through st...
Charin Polpanumas· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Loss spikes in language model pretraining can waste substantial compute and derail otherwise healthy training runs. A primary driver of these instabilities is the growth and divergence of output logits in the final language modeling (LM) head. In this work, we study a particularly costly form of this instability associ...
Zaiqian Chen, Aditya Somasundaram, Sophie Li et al.· 0 citations
Text summarization is an important task for advancing natural language processing (NLP) research and applications in Indic languages. Despite progress in extractive and abstractive summarization, both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these language...
Music audio generation spans instrumental clips, full songs with vocals, edits of existing recordings, and systems that play alongside a musician in real time. This monograph explains the methods behind these systems for readers familiar with neural-network training who are new to music generation. It introduces neural...
M. Modrzejewski, Joanna Kurkowska, Dorien Herremans· 0 citations
Existing code reveals past implementation decisions but rarely explains the reasoning behind them. When coding agents implement new features or modify existing functionality, past decisions may conflict with new task instructions. This raises a fundamental question for agentic software evolution: when multiple implemen...
Haichao Zhu, Geyang Xu, Zhaorui Yang et al.· 0 citations
Current datasets for text-to-video generation are largely limited to short clips depicting a single event or coarse-grained captions. As a result, they provide limited supervision for modeling long-take temporal dependencies, often leading to temporally inconsistent generations when describing multiple events. In this...
Pei-Yuan Zhu, Shao-An Xie, Yi-Fan Shen et al.· 0 citations
Large language models are increasingly used for financial guidance, yet little is known about whether their advice changes across social identities in Global South contexts. We introduce the Indian Financial Automated Advice Bias (IFAAB) benchmark, a counterfactual audit dataset of 31,734 GPT-4o-generated financial-adv...
Robot imitation learning uses demonstrations from operators of varying skill, but selecting training data remains challenging. Existing methods score demonstrations using smoothness, diversity, or estimated influence on policy performance, but differences in selection and evaluation protocols make it difficult to deter...
Coding agents are typically provided end-to-end behavioral specifications that the code they produce should satisfy, such as tests and input--output examples. How many such specifications must a developer provide, and which ones, for the agent to produce the developer's intended program? We argue that this cannot be de...
Aditya Golatkar, Alessandro Achille, Renos Zabounidis et al.· 0 citations
