arXiv:2604.14198v1 Announce Type: new
Abstract: Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tu…
arXiv:2604.14907v1 Announce Type: cross
Abstract: Online hate speech and abusive language pose a growing challenge for content moderation, especially in multilingual settings and for low-resource languages such as Lithuanian. This paper investigates t…
arXiv:2604.15149v1 Announce Type: new
Abstract: As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifiers. We study this phen…
arXiv:2509.02571v2 Announce Type: replace-cross
Abstract: This paper investigates continuous representations of steering vectors over frequency and microphone/source positions for augmented listening (e.g., spatial filtering and binaural rendering), e…
arXiv:2604.14237v1 Announce Type: new
Abstract: Transistor topology optimization is a critical step in standard cell design, directly dictating diffusion sharing efficiency and downstream routability. However, identifying optimal topologies remains a …
arXiv:2604.15096v1 Announce Type: cross
Abstract: Echocardiography is a widely used modality for cardiac assessment due to its non-invasive and cost-effective nature, but the sparse and heterogeneous spatiotemporal views of the heart pose distinct cha…
arXiv:2604.15180v1 Announce Type: new
Abstract: Sparse attention has been proposed as a way to alleviate the quadratic cost of transformers, a central bottleneck in long-context training. A promising line of work is $\alpha$-entmax attention, a differ…
arXiv:2604.15201v1 Announce Type: new
Abstract: As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network ena…
arXiv:2604.14246v1 Announce Type: new
Abstract: Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing long-tail knowledge. We identify that this fragilit…
arXiv:2410.08329v3 Announce Type: replace
Abstract: Computational wave imaging (CWI) extracts hidden structure and physical properties of a volume of material by analyzing wave signals that traverse that volume. Applications include seismic exploratio…