Programming assistants powered by large language models (LLMs) have become widely available, with conversational assistants such as ChatGPT particularly accessible to novice programmers. However, varied tool capabilities and inconsistent availability of extensions (e.g., web search, code execution, retrieval-augmented...
Gabrielle O'Brien, Antonio Pedro Santos Alves, Sebastian Baltes et al.· 0 citations
Granger causality characterizes directed predictive dependencies in multivariate time series, but recovering such dependencies becomes challenging in the presence of latent confounding. Cross-environment invariance provides a natural source of information in heterogeneous settings, yet invariance alone can be insuffici...
Ziyi Zhang, Shaogang Ren, Xiaoning Qian et al.· 0 citations
Can a language model improve reasoning by learning from its own imperfect responses, without rewards or teacher-provided solutions? We present Self-evolving Post-Training (SePT), a simple method that alternates temperature-controlled self-generation with next-token likelihood training. Each round uses the updated model...
Mengqi Li, Lei Zhao, Anthony Man-Cho So et al.· 0 citations
Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the success of separate-encoder approaches like CLIP aligning modality-specific embeddings with contrastive learning, recent multimodal large langu...
Qiyu Wu, Shuyang Cui, Satoshi Hayakawa et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Hybrid thinking enables LLMs to switch between reasoning and direct answering, offering a balance between efficiency and reasoning capability. Yet our experiments reveal that current hybrid thinking LLMs only achieve partial mode separation: reasoning behaviors often leak into the no-think mode. To understand and mitig...
Shouren Wang, Wang Yang, Xianxuan Long et al.· 0 citations
AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent...
Victor May, Diganta Misra, Yanqi Luo et al.· 0 citations
Data-driven inverse optimization for mixed-integer linear programs (MILPs), which seeks to learn an objective function and constraints consistent with observed decisions, is important for building accurate mathematical models in a variety of domains, including power systems and scheduling. However, to the best of our k...
Sequential estimation under partial observability requires tracking beliefs that may be high-dimensional, multimodal, and non-Gaussian. Classical Bayesian filters generalize zero-shot to any system whose dynamics can be evaluated, but their representations scale poorly: parametric filters struggle to capture multimodal...
Christopher Solinas, Radovan Haluska, David Sychrovsky et al.· 0 citations
Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce \emph{false negatives} (rejecting correct answers) and \emph{false positives} (acceptin...
Xin-Qiang Cai, Wei Wang, Feng Liu et al.· 0 citations
Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured sparsity, where nonzeros can appear anywhere, preserves accuracy but yields irregul...
Younes Hourri, Mohammad Mozaffari, Maryam Mehri Dehnavi· 0 citations
Physics-informed graph neural networks (PIGNNs) have emerged as fast AC power-flow solvers that can replace the classic NewtonRaphson (NR) solvers, especially when thousands of scenarios must be evaluated. However, current PIGNNs still need accuracy improvements at parity speed; in particular, the soft constraint on th...
Changhun Kim, Timon Conrad, Redwanul Karim et al.· 0 citations
Autonomous agents executing human instructions must operate reliably even when instructions are incomplete. While recent approaches improve detection of missing information, detection alone is insufficient: agents often proceed to execution even after recognizing underspecification, leading to incorrect or unsafe actio...
Swarnadeep Bhar, Omar Naim, Eleni Metheniti et al.· 0 citations
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
With $2.1 million funding from Google.org, the open-source Public Transit Intelligence Hub will unify public transit monitoring, operations, and passenger communication.
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
