Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
arXiv:2608.11994v1 Announce Type: cross Abstract: We propose claim-level falsification as a principle for test-time scaling and instantiate it through Claim-Level Reliability Assessment (CLR), a training-free framework…
arXiv:2608.11426v1 Announce Type: new Abstract: The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the…
arXiv:2608.11755v1 Announce Type: cross Abstract: Long-form song generation models continue to improve in duration, structural integrity, and acoustic complexity, making reliable aesthetic rewards increasingly important for…
arXiv:2608.11408v1 Announce Type: new Abstract: Prior white-box studies show that large language models can retain latent traces of target knowledge after unlearning, even when the knowledge…
arXiv:2608.00573v2 Announce Type: replace-cross Abstract: Serving Mixture-of-Experts (MoE) large language models across distributed edge servers is bottlenecked by the cross-server expert transmission. The existing approaches mainly…
arXiv:2608.11352v1 Announce Type: new Abstract: Sign language translation has achieved strong results with Transformer architectures, yet recent improvements largely rely on scaling model capacity at the…
arXiv:2608.11236v1 Announce Type: new Abstract: Roleplay evaluation should do more than assign a single score: it should reveal which role requirements were tested, which failed, and…
arXiv:2608.11242v1 Announce Type: new Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks. We identify a class of…
arXiv:2608.11249v1 Announce Type: new Abstract: We study the problem of lossless text compression, motivated by the rapid growth in the collection and storage of digital textual…
arXiv:2608.11338v1 Announce Type: new Abstract: Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents…
arXiv:2608.11332v1 Announce Type: new Abstract: Sign-language research for resource-constrained languages is often limited by the cost of dense linguistic labels such as glosses, temporal boundaries, and…
arXiv:2608.11669v1 Announce Type: cross Abstract: Reinforcement learning against rubrics, lists of criteria graded by an LLM judge, has become a standard way to post-train language models…
arXiv:2608.11350v1 Announce Type: new Abstract: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on…
arXiv:2608.12150v1 Announce Type: cross Abstract: Standard evaluation of large language models assumes stable model rankings across inference conditions. We challenge this assumption by varying the token…
arXiv:2608.11830v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environmental…
arXiv:2604.17244v2 Announce Type: replace Abstract: Large language model (LLM) agents for sequential decision-making struggle to produce diverse outputs. This leads to insufficient exploration, suboptimal solutions, and…
arXiv:2508.02038v5 Announce Type: replace Abstract: This paper presents a multifunctional speech synthesis system that integrates voice cloning and emotion control speech synthesis within a unified framework.…
arXiv:2608.09900v2 Announce Type: replace Abstract: Large language model evaluations typically focus on performance under nominal conditions, creating an illusion of capability where models comfortably walk a…
arXiv:2606.28876v3 Announce Type: replace Abstract: Proposal. Long context can replay history, but it does not decide which completed observations deserve authority. MMLA formalizes a bounded resident…
arXiv:2608.12246v1 Announce Type: cross Abstract: Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first introduce vulnerabilities into codebases.…
arXiv:2608.11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retraining.…
arXiv:2608.12125v1 Announce Type: cross Abstract: As LLM-based agents with user-instructed goals are becoming widely deployed, they increasingly encounter each other in strategic interactions, and face challenges…
arXiv:2608.11226v1 Announce Type: new Abstract: Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized, and datacenters manage GPU…
arXiv:2608.11980v1 Announce Type: cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively…