The Singapore Consensus on Global AI Safety Research Priorities
arXiv:2506.20702v1 Announce Type: new Abstract: Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving…
SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
arXiv:2506.20081v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant…
Exploring Adapter Design Tradeoffs for Low Resource Music Generation
arXiv:2506.21298v1 Announce Type: cross Abstract: Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process,…
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
arXiv:2506.21294v1 Announce Type: cross Abstract: In this paper, we explore the use of a text-only, autoregressive language modeling approach for…
Semantic Scene Graph for Ultrasound Image Explanation and Scanning Guidance
arXiv:2506.19683v2 Announce Type: replace-cross Abstract: Understanding medical ultrasound imaging remains a long-standing challenge due to significant visual variability caused by…
Prover Agent: An Agent-based Framework for Formal Mathematical Proofs
arXiv:2506.19923v1 Announce Type: new Abstract: We present Prover Agent, a novel AI agent for automated theorem proving that integrates large…
AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation
arXiv:2506.19269v2 Announce Type: replace-cross Abstract: We present AnchorDP3, a diffusion policy framework for dual-arm robotic manipulation that achieves state-of-the-art performance…
Off-Policy Evaluation and Learning for the Future under Non-Stationarity
arXiv:2506.20417v1 Announce Type: cross Abstract: We study the novel problem of future off-policy evaluation (F-OPE) and learning (F-OPL) for estimating…