Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

24,787 stories · RSS feed

Hugging Face Trending Papers

Jul 9

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons.

llms computer-vision benchmarks

Hugging Face Trending Papers

Jul 9

CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure.

llms agents benchmarks

arXiv AI

Jul 9

Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control

arXiv:2506. 08630v3 Announce Type: replace Abstract: A universal controller for any robot morphology would greatly improve computational and data efficiency.

By Laurens Engwegen, Max Weltevrede, Caroline Horsch, Daan Brinks, Wendelin B\"ohmer

llms agents reinforcement-learning robotics

arXiv AI

Jul 9

What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study

arXiv:2607. 06799v1 Announce Type: cross Abstract: Evaluating uncertainty in AI-generated SQL queries requires estimating whether a query is correct, where correct means it executes to the same result as a human-written reference.

By Robert Richardson

llms fine-tuning benchmarks data-engineering

arXiv AI

Jul 9

When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs

arXiv:2607. 07395v1 Announce Type: cross Abstract: Reliable confidence estimation remains a key limitation of test-time adaptation in vision-language models (VLMs), where prompt tuning improves zero-shot accuracy but often degrades calibration due to entropy-driven overconfidence.

By Tanay Sodha, Aditya Sharma, Ramya Hebbalaguppe, Vinti Agarwal, Pranav Murthy Yeluripaty

llms rag multimodal benchmarks

arXiv Machine Learning

Jul 9

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

arXiv:2607. 07144v1 Announce Type: new Abstract: The key-value (KV) cache dominates the memory cost of long-context autoregressive inference, and a growing body of work compresses it through quantization, eviction, or offloading.

By Vladimir Gusev

llms efficiency

arXiv AI

Jul 9

Physics-Audited Agentic Discovery in Scientific Machine Learning

arXiv:2607. 07379v1 Announce Type: new Abstract: In agentic scientific machine learning (SciML), large language model (LLM) agents can discover surrogate models and select one by an automated score, typically an error metric.

By Diab W. Abueidda, Bilal Ahmed, Panos Pantidis, Mostafa E. Mobasher

llms agents

arXiv Machine Learning

Jul 9

STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning

arXiv:2607. 06629v1 Announce Type: new Abstract: Brain age -- the age inferred from a physiological recording -- is an emerging biomarker whose deviation from chronological age tracks neurological and psychiatric burden, and EEG is an attractive substrate for it because it is cheap, portable, and temporally rich.

By Roy Segal, Yoni Svechinsky, Tomer Fekete

llms rag nlp fine-tuning benchmarks

arXiv AI

Jul 9

On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces

arXiv:2607. 07375v1 Announce Type: cross Abstract: Adversarial vulnerability in deep neural networks (DNNs) has been studied from the perspectives of decision-boundary geometry, feature robustness, input-output Jacobians, and the instability of inverse problems.

By Chethan Krishnamurthy Ramanaik, Tobias Callies, Michael Hecht, Eirini Ntoutsi

llms multimodal safety

arXiv AI

Jul 9

A Study of Commonsense Reasoning over Visual Object Properties

arXiv:2508. 10956v3 Announce Type: replace-cross Abstract: Inspired by human categorization, visual reasoning about object properties, such as physical attributes and functions, involves identifying and recognizing low-level details and higher-level abstractions.

By Abhishek Kolari, Mohammadhossein Khojasteh, Yifan Jiang, Floris den Hengst, Filip Ilievski

llms nlp multimodal benchmarks

arXiv AI

Jul 9

Successor-Generator Planning with LLM-generated Heuristics

arXiv:2501. 18784v5 Announce Type: replace Abstract: Heuristics are a central component of deterministic planning, particularly in domain-independent settings where general applicability is prioritized over task-specific tuning.

By Alexander Tuisov, Yonatan Vernik, Alexander Shleyfman

llms benchmarks

arXiv AI

Jul 9

RL Post-Training Builds Compositional Reasoning Strategies

arXiv:2607. 07646v1 Announce Type: new Abstract: Does RL post-training merely amplify primitive skills already latent in a base model, or can it compose primitive skills into new higher-level strategies?

By Azwar Abdulsalam, Nishil Patel, Andrew Saxe

llms reinforcement-learning fine-tuning

arXiv AI

Jul 9

Power and Limitations of Aggregation in Compound AI Systems

arXiv:2602. 21556v2 Announce Type: replace Abstract: When designing compound AI systems, a common approach is to query multiple copies of the same model and aggregate the responses to produce a synthesized output.

By Nivasini Ananthakrishnan, Meena Jagadeesan

llms agents

arXiv Machine Learning

Jul 9

Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector

arXiv:2607. 07382v1 Announce Type: new Abstract: Fast Radio Bursts (FRBs) are millisecond-duration radio transients whose automated detection increasingly relies on highly specialized deep learning models.

By Raiff H. Santos, Amilcar R. Queiroz, Tharcisyo S. S. Duarte, K. E. L. de Farias, Rafael A. Batista

llms fine-tuning multimodal benchmarks

arXiv AI

Jul 9

Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning

arXiv:2607. 07117v1 Announce Type: cross Abstract: In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image.

By Stepanida Alekseeva, Jenifer Kalafatovich, Seong-Whan Lee

llms diffusion fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 9

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

arXiv:2607. 07678v1 Announce Type: new Abstract: Rotary Position Embeddings (RoPE) provide transformers with a fixed grid of positional frequencies, yet trained models use these frequencies highly non-uniformly.

By Xinyi Wu, Siyuan Liu, Ali Jadbabaie

llms rag

arXiv AI

Jul 9

Future Confidence Distillation in Large Language Models

arXiv:2607. 07626v1 Announce Type: cross Abstract: Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability.

By Sahil Kale

llms agents efficiency

arXiv AI

Jul 9

Predicting LLM Safety Before Release by Simulating Deployment

arXiv:2607. 07184v1 Announce Type: cross Abstract: Pre-deployment safety evaluations aim to inform the downstream risks of releasing a new AI model.

By Marcus Williams, Hannah Sheahan, Cameron Raymond, Tomek Korbak, Deng Pan, Peilin Yang, Leon Maksin, Ningyi Xie, Phillip Guo, Ian Kivlichan, Micah Carroll

llms safety

arXiv AI

Jul 9

Measuring the metacognition of AI

arXiv:2603. 29693v3 Announce Type: replace Abstract: A robust decision-making process must take into account uncertainty, especially when the choice involves inherent risks.

By Richard Servajean, Philippe Servajean

llms

arXiv AI

Jul 9

Large Language Models (LLMs) and Generative AI in Cybersecurity and Privacy: A Survey of Dual-Use Risks, AI-Generated Malware, Explainability, and Defensive Strategies

arXiv:2607. 06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automated defense and sophisticated attacks.

By Kiarash Ahi, Saeed Valizadeh

llms diffusion benchmarks safety

Get the daily briefing