LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2606. 12690v1 Announce Type: cross Abstract: In this paper, we propose the Enhanced World Action Model (EWAM), a closed-loop online adaptation architecture built upon a pretrained and fully frozen Cosmos3 backbone network.
arXiv:2606. 12657v1 Announce Type: new Abstract: Human mobility data is important for transportation, urban planning, and epidemic control, but large-scale trajectory collection is often costly and privacy-constrained, motivating realistic synthetic trajectory generation.
arXiv:2606. 12910v1 Announce Type: cross Abstract: For robotics to be effectively integrated into household or industrial environments, machines must adapt to natural-language prompts in real time.
arXiv:2606. 12942v1 Announce Type: new Abstract: Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in long-context multimodal scenarios.
arXiv:2606. 13038v1 Announce Type: new Abstract: As LLM agents proliferate in prediction markets and collective decision-making, they risk a cognitive monoculture: agents built on shared foundation models produce correlated forecasts, and recent measurement finds frontier-model errors correlated at r ~ 0.
arXiv:2606. 12485v1 Announce Type: cross Abstract: Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach.
arXiv:2606. 13477v1 Announce Type: cross Abstract: Supramolecular chemistry, which includes the study of non-covalent host-guest assemblies, has advanced various applications.
arXiv:2606. 12886v1 Announce Type: cross Abstract: Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks.
arXiv:2605. 03847v2 Announce Type: replace Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates environments in which emergent risk is structurally unavoidable: locally correct decisions by individual agents compose into globally unacceptable behavioral trajectories under uncertainty.
arXiv:2606. 13647v1 Announce Type: cross Abstract: We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language, comprising 31 datasets across 7 task types -- nearly 4$\times$ the depth of existing multilingual benchmark coverage for Slovak.
Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation.
Computer-Aided Design is pivotal in modern manufacturing, yet existing automated methods predominantly rely on open-loop, one-shot generation, creating a mismatch with iterative real-world practices. In this paper, we present IterCAD, a unified multimodal agent framework for closed-loop, interactive CAD generation and editing.
Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence.
Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in long-context multimodal scenarios. We identify a recurring failure mode, parse collapse, where the autoregressive decoder produces fluent yet incomplete rankings by silently omitting candidates and terminating early.
Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in complex long-chain scenarios, we identify a fundamental failure mode: generated images diverge from the textual context while subsequent text ignores the visual evidence, causing the two modalities to alternate without genuinely informing each other.
In Low-Rank Adaptation (LoRA), the scaling factor $α$ is often treated as a mere complement to the learning rate, yet its role in optimization remains poorly understood. In this paper, we reveal that the scaling factor $α$ and the learning rate function differently, with $α$ emerging as the dominant driver of effective optimization, delivering gains that cannot be replicated by learning rate scaling alone.
arXiv:2606. 12032v1 Announce Type: new Abstract: Contemporary AI alignment research treats self-preservation as an instrumental nuisance to be suppressed by external mechanisms.
arXiv:2606. 11279v1 Announce Type: cross Abstract: Automatic speech recognition systems have been shown to under-perform when it comes to transcribing words rarely seen in the training data, namely specialized terminology.
arXiv:2601. 21898v2 Announce Type: replace Abstract: The rise of model hubs has made it easier to access reusable model components, making model merging a practical tool for combining capabilities.
arXiv:2606. 11386v1 Announce Type: cross Abstract: Full-duplex spoken language models (FD-SLMs) enable seamless speech interaction by allowing models to listen and speak simultaneously, yet the internal mechanism by which they coordinate listening and speaking remains underexplored.