Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
Zero-shot anomaly detection aims to localize anomalies without target-domain samples. Existing CLIP-based methods suffer from coarse anomaly maps and limited semantic prompts. We propose PSMP-CLIP, in...
Image segmentation remains challenging due to occlusions, poor lighting, and irregular structures. Although transformer-based methods achieve high accuracy, they rely heavily on long-range spatial fea...
With the rapid development of Large language model (LLM), agent systems enhanced by LLMs show huge potential in being able to deal with complex tasks, especially involving multi-step thinking or inter...
Fine-tuning an aligned language model on narrow, flawed data can induce harmful behavior far outside the training domain, known as emergent misalignment (EM). Prior work has localized EM in model weig...
Category-level object pose estimation seeks to recover a similarity transform $(R,t,s)$ for unseen instances without instance-specific CAD models. Most competitive methods are correspondence-based: pr...
Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates context windows and incurs prohibitive costs. Curre...
Large-scale vision-language models (VLM) such as CLIP enable strong open-vocabulary reasoning, yet deploying these capabilities on resource-constrained edge devices remains challenging. EdgeVL address...
Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additional iterations can reduce support for a reference an...
Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritize...
KV-cache eviction perturbs the conditional token distributions governing autoregressive generation. We investigate how first-divergence timing and subsequent token mismatch determine cumulative disagr...
Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, p...
arXiv:2609.13984v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models combine a pretrained vision encoder, a language backbone, and an action head, but their relative contribution has...
arXiv:2602.21061v2 Announce Type: replace Abstract: Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve com...
arXiv:2609.13734v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing...
arXiv:2609.15533v1 Announce Type: cross Abstract: Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inheren...
arXiv:2607.10198v2 Announce Type: replace Abstract: Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these in...
arXiv:2609.15205v1 Announce Type: cross Abstract: Table extraction from texts is an important task for information systems, and recent approaches that prompt large language models (LLMs) with instruc...
arXiv:2410.14083v2 Announce Type: replace Abstract: This paper describes a new spatial correspondence representation based on paired regions-of-interest (ROIs), for medical image registration. The di...
arXiv:2509.24975v4 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) enable parallel generation and are promising for unit test generation (UTG), where efficient and larg...
arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...