arXiv:2609.00067v2 Announce Type: replace-cross Abstract: External text can override conflicting image evidence in multimodal large language models, a failure we call multimodal contextual sycophancy. We introduce a 998-case diagnostic that…
arXiv:2608.29507v2 Announce Type: replace-cross Abstract: Diffusion models are increasingly used not only for sampling from learned data distributions, but also for generating samples that optimize task-specific objectives. A common approach is to…
arXiv:2608.27406v2 Announce Type: replace-cross Abstract: State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that…
arXiv:2608.26105v2 Announce Type: replace-cross Abstract: Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered…
arXiv:2608.22076v3 Announce Type: replace-cross Abstract: Rising energy demand, fossil fuel depletion and climate change highlight the need for more efficient energy production and consumption. Offshore oil and gas platforms face challenges related…
arXiv:2608.21099v2 Announce Type: replace-cross Abstract: Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Recent vision foundation models (e.g…
arXiv:2608.18234v3 Announce Type: replace-cross Abstract: Whole-body motion tracking policies turn a humanoid into a robust control interface: the teleoperator---or an upstream model---only supplies a coarse movement intent, while the low-level…
arXiv:2608.18138v2 Announce Type: replace-cross Abstract: In recent years, the rapid development of language models has transformed the field of Natural Language Processing through a wide range of applications. However, the development of language…
arXiv:2608.16696v2 Announce Type: replace-cross Abstract: Lossy compression is conventionally driven by a task-agnostic distortion (e.g., MSE or MS-SSIM), yet in many emerging applications the receiver cares not about uniform fidelity but about a…
arXiv:2608.15424v2 Announce Type: replace-cross Abstract: The rapid adoption of large language models has enabled the development of clinical multi-agent systems (MAS) capable of integrating multimodal patient data and supporting increasingly…
arXiv:2608.10906v3 Announce Type: replace-cross Abstract: An agent skill is a folder containing a SKILL.md file with instructions for a language-model agent, optionally accompanied by scripts and reference files. The agent loads the skill when it…
arXiv:2608.00583v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) monitors are reported by their aggregate accuracy on a pool of reward hacks. We show that this number is a false average. On Terminal Wrench, about 77% of hacks are…
arXiv:2608.00183v2 Announce Type: replace-cross Abstract: Retrieval over financial filings is difficult because queries are short and acronym-heavy while the answer-bearing evidence sits inside long, table-dense documents. We study sparse-dense…
arXiv:2607.07033v5 Announce Type: replace-cross Abstract: Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query. Existing…
arXiv:2607.05276v2 Announce Type: replace-cross Abstract: Speaker embeddings, or x-vectors, are widely used to represent speaker identity and speaker-related attributes, but existing embedding extractors are typically descriptive rather than…
arXiv:2606.23989v5 Announce Type: replace-cross Abstract: Large language models produce fluent multi-document summaries, but their attributions are typically coarse---whole documents or passages---and generated post hoc, leaving each statement hard…
arXiv:2606.21203v2 Announce Type: replace-cross Abstract: Psycholinguistics studies show that human readers fall for coherence illusions: an incoherent discourse can seem coherent simply because a distractor matches what comes next. We investigate…
arXiv:2606.20474v3 Announce Type: replace-cross Abstract: Context-heavy agents place substantial pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can…
arXiv:2606.10531v3 Announce Type: replace-cross Abstract: Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs). Current QAT methods are mainly based on scalar quantization (SQ), which enables efficient…
arXiv:2606.10388v3 Announce Type: replace-cross Abstract: Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent. This makes…
arXiv:2606.10380v3 Announce Type: replace-cross Abstract: Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts. When applied to multi-turn dialogues, current models exhibit significant…
arXiv:2606.08644v2 Announce Type: replace-cross Abstract: To interpret context correctly and retrieve relevant information, large language models must bind entities to their attributes and update these bindings as state changes. We analyze how LLMs…
arXiv:2606.07167v2 Announce Type: replace-cross Abstract: Meaningful multilingual evaluation must test models in the target language and educational context. Urdu, spoken by more than 230 million people, lacks a broad MMLU-style benchmark built…
arXiv:2606.05402v2 Announce Type: replace-cross Abstract: Large reasoning models (LRMs) produce reasoning traces with non-linear structures, such as backtracking and self-correction, that complicate the evaluation and monitoring of the reasoning…
Pick what should wake you up. We only push stories the AI rates as genuinely urgent.