Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.30773v1 Announce Type: new Abstract: Tandem speech-to-speech architectures couple a responsive speech frontend with an asynchronous text ba…
arXiv:2609.30739v1 Announce Type: new Abstract: Multilingual text-vision embedding models are essential for cross-lingual image-text retrieval, but So…
arXiv:2609.30670v1 Announce Type: new Abstract: Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluat…
arXiv:2609.30652v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student model by having it generate trajectories, then matching…
arXiv:2609.30547v1 Announce Type: new Abstract: Audience sizing is a critical component of digital marketing. It enables precise resource allocation,…
arXiv:2609.30535v1 Announce Type: new Abstract: Children in multilingual communities often code-switch, using multiple languages in a single utterance…
arXiv:2609.30467v1 Announce Type: new Abstract: Retrieval-based factuality evaluation, where LLM-generated claims are verified against evidence from a…
arXiv:2609.30439v1 Announce Type: new Abstract: We introduce target-speaker unlearning ASR (TSU-ASR) task in a fully end-to-end framework for multi-sp…
arXiv:2609.30416v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong performance in low-resource offline translation; howeve…
arXiv:2609.30298v1 Announce Type: new Abstract: Systematic reviews (SR) are essential for evidence-based research, but their screening phase is highly…
arXiv:2609.30289v1 Announce Type: new Abstract: In team collaboration scenarios, memory is heterogeneous and continually evolving. Team memories captu…
arXiv:2606.28639v3 Announce Type: replace-cross Abstract: We establish mathematical limits of algorithmic safety verification for Turing-complete self…
arXiv:2605.26114v3 Announce Type: replace-cross Abstract: We present MobileGym, a browser-hosted, lightweight, fully controllable environment for ever…
arXiv:2605.11750v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where mi…
arXiv:2605.03228v2 Announce Type: replace-cross Abstract: As large language model (LLM)-powered agents are increasingly deployed to perform complex, r…
arXiv:2604.15558v2 Announce Type: replace-cross Abstract: Deliberative multi-agent systems allow agents to exchange messages and revise beliefs over t…
arXiv:2603.27001v2 Announce Type: replace-cross Abstract: Speaker anonymization (SA) systems modify timbre while leaving regional or non-native accent…
arXiv:2603.13768v2 Announce Type: replace-cross Abstract: Despite the strong performance of large audio language models (LALMs) in various tasks, exac…
arXiv:2602.16715v2 Announce Type: replace-cross Abstract: We explore the potential of Large Language Models (LLMs), Retrieval-Augmented Generation (RA…
arXiv:2601.13566v2 Announce Type: replace-cross Abstract: Can language models improve their accuracy without external supervision? Methods such as deb…