For languages with limited resources, Sentiment Analysis remains a challenging problem due to limited annotated data and strong domain variability across textual sources. Marathi, despite being widely spoken, lacks extensive multi-domain sentiment analysis studies. Recent efforts by L3Cube have introduced multi-domain...
Tanvi Somani, Aryan Babare, Samyak Bora et al.· 0 citations
Sentiment analysis is a key task in Natural Language Processing that determines the polarity of opinions in text. For low-resource languages like Marathi--where limited data prevents the direct use of standard statistical methods--models are often trained on single-domain datasets. While this yields strong in-domain pe...
Tanvi Somani, Aryan Babare, Samyak Bora et al.· 0 citations
This work introduces AlphaPilot, a reinforcement-learning framework that trains multi-turn tool-using LLM agents for adaptive alpha mining, and attains the highest mean total return, Sharpe, and RankIC among the evaluated methods on both universes.
Pei-Qi Jiang, Fan Zhang, Xin Xu et al.· 0 citations
Retrieval-augmented generation (RAG) reuses the same documents across many requests, making non-prefix KV-cache reuse attractive. Yet a cached document state is not reusable text: it is a context-conditioned causal state whose keys and values depend on the prefix, position, and preceding documents under which it was co...
Xingjian Zhang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A language model's ability to solve a task individually does not ensure that a team can solve it under unequal access to information and communication. SANZARU examines this gap through cooperative bomb-defusal puzzles adapted from BOMBANANA! (Lefto Studio, 2026). Task information and action authority are divided among...
This work studies what shapes citation in two 90-day collections of answers to commercial questions in contrasting markets, and controlled experiments show that brand names reorder its rankings of products with identical facts.
Embedding models underpin modern job-candidate matching: resumes, job descriptions, and queries are encoded as dense vectors, and recommendations come from nearest-neighbor retrieval over that space. Any social bias in the embeddings therefore feeds directly into HR recommendations. We audit six multilingual sentence-e...
This work derives data mixing scaling laws for three modalities: text, vision, and audio from Mixture-of-Experts (MoE) architectures, and provides a principled foundation for understanding the multimodal data mixtures needed to train frontier MLLMs.
Aditi Khandelwal, A. Tarun, Yi-Xuan Xu et al.· 0 citations
Reinforcement learning (RL) has driven substantial progress in coding agents by relying on verified successful trajectories as learning signals. However, such trajectories are scarce in long-horizon software engineering tasks, where a minor error can invalidate the entire rollout. Repeatedly restarting from the initial...
Mengyang Liu, Wei-Ming Wang, Hai-Xin Nan et al.· 2 citations
Late-interaction (multi-vector) models represent documents using a set of token-level vectors, providing a middle ground between cross-encoders and dense encoders in terms of quality and cost of embedding. However, compared to the latter, the indices are costly to store and score. Pooling and pruning based compression...
Terminal agents solve tasks in software engineering and scientific research by executing commands in a terminal. Training them via reinforcement learning (RL) requires diverse and verifiable environments, but these environments are still mostly designed by human researchers, so their supply grows only as fast as resear...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
