arXiv:2604.02341v1 Announce Type: new Abstract: Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such pipelines optimize outcome correctness only,…
arXiv:2604.02342v1 Announce Type: new Abstract: In recent years, Graph Neural Networks (GNNs) have achieved remarkable success in tasks such as node classification, link prediction, and graph representation learning. However, they remain susceptible to biases that can arise not only from…
arXiv:2604.02340v1 Announce Type: new Abstract: Recent advances in masked diffusion language models (MDLMs) narrow the quality gap to autoregressive LMs, but their sampling remains expensive because generation requires many full-sequence denoising passes with a large Transformer and, unlike autoregressive decoding,…
arXiv:2604.02339v1 Announce Type: new Abstract: Natural language context-such as instructions, knowledge, or feedback-contains rich signal for adapting language models. While in-context learning provides adaptation via the prompt, parametric learning persists into model weights and can improve performance further, though is…
arXiv:2604.02338v1 Announce Type: new Abstract: MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability to adapter-based architectures. We propose…
arXiv:2405.15314v5 Announce Type: replace Abstract: Incorporating domain-specific constraints into machine learning models is essential for generating predictions that are both accurate and feasible in real-world applications. This paper introduces new methods for training Output-Constrained Regression Trees (OCRT), addressing the limitations…
arXiv:2604.02344v1 Announce Type: new Abstract: WebGPU’s security-focused design imposes per-operation validation that compounds across the many small dispatches in neural network inference, yet the true cost of this overhead is poorly characterized. We present a systematic characterization of WebGPU dispatch…
arXiv:2509.21716v2 Announce Type: replace Abstract: Harnessing parallelism in seemingly sequential models is a central challenge for modern machine learning. Several approaches have been proposed for evaluating sequential processes in parallel using iterative fixed-point methods, like Newton, Picard, and Jacobi iterations.…
arXiv:2604.02345v1 Announce Type: new Abstract: Scaling generalist GUI agents is hindered by the data scalability bottleneck of expensive human demonstrations and the “distillation ceiling” of synthetic teacher supervision. To transcend these limitations, we propose UI-Oceanus, a framework that shifts the…
arXiv:2601.21064v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as part of compound AI systems that coordinate multiple modules (e.g., retrievers, tools, verifiers) over long-horizon workflows. Recent approaches that propagate textual feedback globally (e.g., TextGrad) make it…
