arXiv:2608.04312v1 Announce Type: cross Abstract: Recent proliferation of data-optimization integration has led to a range of methods that aim to improve the statistical performance of data-driven…
arXiv:2608.05138v1 Announce Type: cross Abstract: Modern Greek is absent from NVIDIA's Nemotron retrieval models and from major multilingual retrieval benchmarks, despite being important for retrieval-augmented generation…
arXiv:2602.11745v2 Announce Type: replace Abstract: Graph models are fundamental to data analysis in domains rich with complex relationships. Unlike SQL, which benefits from a rel- atively…
arXiv:2608.04056v1 Announce Type: new Abstract: When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism…
arXiv:2607.10082v2 Announce Type: replace Abstract: Building pixel-level correspondence between event and image data is a fundamental task for multi-sensor systems. However, existing cross-modal matching methods are…
arXiv:2608.04244v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) make grounded predictions in real-world scenes by combining visual and textual cues, yet existing benchmarks rarely…
arXiv:2602.05869v3 Announce Type: replace-cross Abstract: We introduce Wedge Sampling, a new non-adaptive sampling scheme for low-rank tensor completion. We study recovery of an order-$k$ low-rank tensor…
arXiv:2405.18220v4 Announce Type: replace Abstract: Tensor-based discrete density estimation requires flexible modeling and proper divergence criteria to enable effective learning; however, traditional approaches using $alpha$-divergence face…
arXiv:2507.03897v3 Announce Type: replace-cross Abstract: We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images.…
arXiv:2608.04205v1 Announce Type: new Abstract: Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but…
arXiv:2608.04384v1 Announce Type: new Abstract: Neural PDE solver auto-design is fundamentally a search-space representation problem. In the space of unrestricted Python programs, valid solvers form an…
arXiv:2608.04037v1 Announce Type: new Abstract: Designing narrative-grounded interactive experiences remains labor-intensive because interactive content must align with the underlying world implied by the narrative. Existing approaches…
arXiv:2608.03991v2 Announce Type: replace Abstract: Training-free open-vocabulary semantic segmentation (OVSS) partitions an image into semantically distinct regions based on arbitrary text descriptions, without learning any additional…
arXiv:2605.19607v2 Announce Type: replace Abstract: Integrated Gradients (IG) is a widely adopted feature attribution method that satisfies desirable axiomatic properties. However, the choice of integration path…
arXiv:2608.04048v1 Announce Type: new Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization…
arXiv:2511.09002v3 Announce Type: replace Abstract: Self-consuming generative models have received significant attention over the last few years. In this paper, we study a self-consuming generative model…
arXiv:2608.04339v1 Announce Type: cross Abstract: Large language models are increasingly used for information seeking, yet semantically equivalent questions phrased in different ways can receive answers of…
arXiv:2608.04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present…
arXiv:2608.01742v2 Announce Type: replace Abstract: Long-term memory is critical for LLM agents operating over long-horizon interactions. However, several persistent limitations of existing memory systems can be…
arXiv:2604.05087v3 Announce Type: replace Abstract: Document expansion is a classical technique for improving retrieval quality, and is attractive since it shifts computation offline, avoiding additional query-time…
arXiv:2512.03590v3 Announce Type: replace Abstract: Existing talking-head generation methods primarily target open-ended generation rather than bridging two existing video segments. In this paper, we study talking-head…
arXiv:2608.04292v1 Announce Type: new Abstract: The proliferation of agentic artificial intelligence (AI) systems has raised serious questions about the accountability for tasks performed by AI agents.…
arXiv:2605.28566v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, yet their standard generation process -- auto-regressive token prediction -- is inherently…
arXiv:2605.24212v2 Announce Type: replace-cross Abstract: Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are…