LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2607. 10455v1 Announce Type: new Abstract: Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight.
arXiv:2602. 17993v2 Announce Type: replace-cross Abstract: Complex problems, whether in math, logic, or planning, are solved by humans through a sequence of steps where the result of one step informs the next.
arXiv:2604. 00878v2 Announce Type: replace-cross Abstract: Actor-level stance detection aims to determine an author expressed position toward specific geopolitical actors mentioned or implicated in a text.
arXiv:2607. 11798v1 Announce Type: cross Abstract: Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film.
arXiv:2607. 11839v1 Announce Type: cross Abstract: This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity recognition in healthcare-oriented training environments.
arXiv:2607. 11801v1 Announce Type: cross Abstract: Large audio-language models (LALMs) often underperform on fine-grained, non-semantic attributes of speech, such as a speaker's emotion, despite strong performance on speech content.
arXiv:2607. 11862v1 Announce Type: cross Abstract: Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding.
arXiv:2607. 11578v1 Announce Type: cross Abstract: Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less than 10\% of clinical recordings.
arXiv:2607. 11119v1 Announce Type: cross Abstract: Robot manipulation is a complex task that requires visual understanding, physical reasoning, planning, and closed-loop control.
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
arXiv:2607. 09796v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has become an important method for aligning large language models (LLMs) with human preferences because it removes the need for explicit reward modeling and reinforcement learning optimization.
arXiv:2607. 09842v1 Announce Type: new Abstract: We investigate whether identity-specifying system prompts produce statistically distinguishable geometric fingerprints in the hidden-state trajectories of four open-weight transformer language models spanning four post-training regimes: no training (Gemma-4-E4B base), multimodal RLHF (Gemma-4-E4B-it), RL distillation (DeepSeek-R1-Distill-Qwen-7B), and SFT (Qwen2.
arXiv:2506. 20893v5 Announce Type: replace-cross Abstract: In this paper, we reveal a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause information leakage about the forgotten class.
arXiv:2607. 10312v1 Announce Type: cross Abstract: The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts.
arXiv:2607. 10630v1 Announce Type: cross Abstract: Robust motion planning in dense traffic requires autonomous vehicles to interact in rare and safety-critical scenarios that are underrepresented in naturalistic driving data.
arXiv:2607. 10127v1 Announce Type: cross Abstract: Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery.
arXiv:2607. 10517v1 Announce Type: cross Abstract: Activation steering offers a lightweight alternative to fine-tuning for controlling large language models at inference time.
arXiv:2607. 09825v1 Announce Type: cross Abstract: Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid.
arXiv:2607. 10299v1 Announce Type: new Abstract: Recent advances in large-scale multimodal models have drivenremarkable progress in vision-language tasks; however, comprehensiveomni-modal understanding remains under-explored, largely due to thescarcity of datasets with rich, explicitly aligned auditory cues.
arXiv:2607. 10159v1 Announce Type: new Abstract: In real-world multimodal web scenarios, graph-structured data often arrives in a streaming manner, making graph continual learning a crucial paradigm for continuously modeling such evolving structures.