Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2403.17612v3 Announce Type: replace Abstract: Labeling corpora constitutes a bottleneck to create models for new tasks or domains. Large language models mitigate the issue with automatic corpus...
arXiv:2505.23126v5 Announce Type: replace Abstract: Although many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs) within domains such as mathematics, coding, or data wrang...
The paper argues that hallucinations by legal language models should be judged as failures of legal warrant rather than mere factual or citation errors. It defines claim-authority warrant as a context-sensitive relationship between a legal claim and applicable, current authority, and proposes that evaluating warrant can uncover failures missed by traditional accuracy or citation metrics. The authors outline a pilot study, benchmark specifications, and a research agenda to assess whether legal AI systems’ claims are properly licensed by law.
arXiv:2602.02377v3 Announce Type: replace Abstract: While large language models (LLMs) have achieved strong performance on mathematical problems with verifiable answers, many advanced problems are pr...
arXiv:2602.15868v3 Announce Type: replace Abstract: Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic...
The paper investigates whether large language models (LLMs) can generate synthetic cyberbullying conversations that replicate the social dynamics of real interactions. Using a comprehensive framework, the authors compare authentic dialogues with synthetic ones from GPT, Grok, and LLaMA across structural, linguistic, affective, and temporal dimensions, and conduct human evaluations of realism. Results show that while LLMs preserve high‑level interaction patterns, they systematically distort finer‑grained social phenomena, with model‑specific biases such as GPT’s suppression of harmful content and Grok’s amplification of aggression.
RankGround is a two‑stage framework for GUI grounding that uses a single Vision‑Language Model call per query. It introduces GroundRanker, a lightweight multimodal reranker that selects the most promising crop from a dense candidate set, trained with a two‑stage curriculum on ranking supervision data derived from existing grounding datasets. Experiments show RankGround outperforms strong baselines, achieving 1.4× faster inference and a 5.5% average improvement in localization accuracy over the second‑best method across all backbones and screen scales.
arXiv:2607.28077v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identica...
The paper introduces Code Consistency Preference Optimization Verification (CCPO), a method that generates computationally sound solutions with dependency graphs to improve execution-consistent preference optimization for language models. By building a scientific reasoning dataset and extracting reasoning steps, prerequisites, and derivability relationships, the authors compute execution consistency scores that are used to fine‑tune models such as Llama‑3‑8B and DeepSeekMath‑7B, achieving significant performance gains on MATH (+17.0%) and GSM8K (+15.1%). The extended Scientific Feasibility Control framework further boosts accuracy on PhyX physics reasoning to 50.1%, surpassing existing models while maintaining high scientific validity and reducing law violations.
arXiv:2509.21891v3 Announce Type: replace-cross Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been...
arXiv:2609.17545v1 Announce Type: new Abstract: Deep learning models for cervical cytology are almost always evaluated as if every prediction must be acted upon, yet a screening system deployed along...
arXiv:2609.18345v1 Announce Type: new Abstract: Large vision-language models (LVLMs) are commonly used with only a single text prompt as the input, or plus an image. In this paper, we demonstrate tha...
arXiv:2609.18037v1 Announce Type: new Abstract: Segment Anything Models provide reusable priors, yet they require user prompts and cannot support fully automatic instrument segmentation. Automatic pr...
The paper investigates which demographic attributes large language models (LLMs) default to when annotating text without explicit demographic cues. By comparing non‑demographic, placebo‑conditioned, and demographic‑conditioned prompts on politeness and offensiveness tasks in the POPQUORN dataset, the authors find that LLMs exhibit notable gender, race, and age influences in their annotations. This contrasts with earlier studies that reported no such effects, highlighting the importance of considering demographic bias in LLM‑based annotation workflows.
arXiv:2609.18125v1 Announce Type: new Abstract: Humans often observe others before interacting and adjust their behavior accordingly. Robot navigation in crowds, however, often represents pedestrians...
arXiv:2609.18955v1 Announce Type: new Abstract: Efficient perception models are essential for real-time autonomous driving, where accuracy and computational cost must be carefully balanced. However,...
arXiv:2609.18971v1 Announce Type: new Abstract: Surgical phase recognition maps each video frame to a clinically meaningful workflow phase, supporting context-aware assistance, documentation, and pos...
arXiv:2609.18510v1 Announce Type: new Abstract: We present DiT-Garment to model dynamic 3D clothing over human body models in arbitrary motion. Unlike existing methods, DiT-Garment can animate garmen...
arXiv:2609.18578v1 Announce Type: new Abstract: Pathologists diagnose diseases by first locating suspicious tissue and then examining it at higher magnification, whereas self-supervised vision transf...
arXiv:2609.18602v1 Announce Type: new Abstract: Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly...