Large language models

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

20,725 stories · RSS feed

arXiv AI

Jul 22

Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

arXiv:2607. 19344v1 Announce Type: cross Abstract: Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone.

By Rahul Sajnani, Yulia Gryaditskaya, Radom\'ir M\v{e}ch, Srinath Sridhar, Matheus Gadelha

llms diffusion multimodal

arXiv AI

Jul 22

FormGym: Doing Paperwork with Agents

arXiv:2506. 14079v4 Announce Type: replace Abstract: Completing paperwork is a challenging and time-consuming problem.

By Matthew Toles, Rattandeep Singh, Isaac Song, Zhou Yu

llms agents computer-vision multimodal benchmarks

arXiv AI

Jul 22

Soft-TransFormers for Continual Learning

arXiv:2411. 16073v4 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transformer through task-specific soft subnetworks: real-valued multiplicative masks over the query, key, value, and output projections of selected self-attention layers.

By Haeyong Kang, Chang D. Yoo

llms fine-tuning benchmarks

arXiv AI

Jul 22

Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality

arXiv:2607. 03691v2 Announce Type: replace-cross Abstract: Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agent harness: a middleware layer in between a developer and a large language model that orchestrates system prompts, tool execution, context management, and iterative reasoning loops.

By Oussama Ben Sghaier, Hao Li, Bram Adams, Ahmed E. Hassan

llms agents

arXiv AI

Jul 22

From Dependency to Compositionality: A Neurosymbolic Lifting of LLM Outputs via Combinatory Categorial Grammar

arXiv:2607. 18961v1 Announce Type: new Abstract: Large language models (LLMs) generate fluent text by incrementally predicting the next token from a prefix.

By Remo Pareschi

llms data-engineering

arXiv Machine Learning

Jul 22

On the Limits of Support-Preserving Alignment and Bounded Filtering

arXiv:2607. 18295v1 Announce Type: new Abstract: We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability of harmful behavior to zero in modern large language models.

By Aryan Dutt, Rui Mao, Anupam Chattopadhyay

llms benchmarks safety

arXiv AI

Jul 22

Assessment in Team Problem-Solving Exercises in Computing Education

arXiv:2607. 19209v1 Announce Type: cross Abstract: This full paper in the research-to-practice track presents methods for assessing student teams in tabletop exercises (TTXs).

By Valdemar \v{S}v\'abensk\'y, Jan Vykopal, Sukrit Leelaluk, Pavel \v{C}eleda, Fumiya Okubo, Atsushi Shimada

llms

arXiv AI

Jul 22

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information

arXiv:2607. 19313v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models.

By Priyank Agrawal, Ankur Samanta, Shervin Ghasemlou, Jalaj Bhandari, Kavosh Asadi, Daniel Jiang, Aditya Modi

llms reinforcement-learning benchmarks

arXiv AI

Jul 22

The Information Shadow: Measuring Structural Limits on What Language Models Can Learn

arXiv:2607. 18305v1 Announce Type: cross Abstract: Some limits on what language models know are not gaps in data coverage but structural properties of learning from text.

By Priyansh Srivastava, Romit Chatterjee

llms benchmarks safety

arXiv Machine Learning

Jul 22

HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks

arXiv:2607. 18867v1 Announce Type: new Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks.

By Haozhe Jia

llms robotics efficiency

arXiv Machine Learning

Jul 22

Optimizing Regret

arXiv:2607. 18866v1 Announce Type: cross Abstract: Building on the identity that expected regret equals the covariance between costs and decisions, this paper develops the complete derivative theory of the covariance regret functional.

By Irene Aldridge

llms

arXiv AI

Jul 22

When Visual Evidence is Ambiguous: Pareidolia as a Diagnostic Probe for Vision Models

arXiv:2603. 03989v2 Announce Type: replace-cross Abstract: When visual evidence is ambiguous, vision models must decide how to interpret face-like patterns.

By Qianpu Chen, Derya Soydaner, Rob Saunders

llms computer-vision multimodal safety

arXiv AI

Jul 22

AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System

arXiv:2607. 18825v1 Announce Type: cross Abstract: This comprehensive study introduces an advanced Artificial Intelligence for Indian Legal Question Answering (AILQA) system tailored to the Indian legal context.

By Shubham Kumar Nigam, Shubham Kumar Mishra, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

llms rag nlp benchmarks safety

arXiv AI

Jul 22

Physics-Guided Masked Multi-Task Network for Edge-Friendly Battery Health Diagnostics from Sto-chastically Fragmented Charging Profiles

arXiv:2607. 18330v1 Announce Type: cross Abstract: The deployment of reliable lithium-ion battery management systems is crucial for accelerating electrification, yet the joint prognosis of State of Health (SOH) and Remaining Useful Life (RUL) remains severely hindered by task heteroscedasticity.

By Shuhao Chen, Tianyu Shi, Chengyi Tu

llms rag benchmarks

arXiv AI

Jul 22

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

arXiv:2607. 18367v1 Announce Type: new Abstract: Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly.

By AlayaWorld Team, Kaipeng Zhang, Chuanhao Li, Yifan Zhan, Yongtao Ge, Yuanyang Yin, Jiaming Tan, Kang He, Liaoyuan Fan, Mingliang Zhai, Ruicong Liu, Xiaojie Xu, Xuangeng Chu, Zhen Li, Zhengyuan Lin, Zhixiang Wang, Zian Meng, Zihui Gao

llms diffusion efficiency

arXiv Machine Learning

Jul 22

A Classifier That Teaches Itself: Self-Improving, Frozen-gate Training (SIFT) for Dynamic Document Classification

arXiv:2607. 18358v1 Announce Type: cross Abstract: Document classification is a solved problem in the laboratory and an unsolved one in the enterprise.

By Bogdan Raduta, Horia Velicu, Alexandru Preda, Serban Chiricescu

llms safety

arXiv AI

Jul 22

Dynamic Loss Balancing for Joint SOH and RUL Prediction of Lithium-Ion Batteries via a Rotary SOH-Injected Prior Battery Transformer

arXiv:2607. 18329v1 Announce Type: cross Abstract: The deployment of reliable lithium-ion battery management systems is crucial for accelerating electrification, yet the joint prognosis of State of Health (SOH) and Remaining Useful Life (RUL) remains severely hindered by task heteroscedasticity.

By Shuhao Chen, Tianyu Shi, Yiwen Huang, Chengyi Tu

llms rag benchmarks

arXiv Machine Learning

Jul 22

H$^2$SD: Hybrid Hindsight Self-Distillation

arXiv:2607. 18955v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models on tasks such as mathematical reasoning and code generation.

By Qiye Cai, Yichuan Ma, Linyang Li, Peiji Li, Yongkang Chen, Qipeng Guo, Yicheng Zou, Tao Gui, Xiaocheng Feng, Bing Qin

llms reinforcement-learning efficiency benchmarks

arXiv AI

Jul 22

PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents

arXiv:2607. 18859v1 Announce Type: new Abstract: While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of repair strategies.

By Tianyue Jiang, Yanlin Wang, Xin He, Daya Guo, Jiachi Chen, Ming Wen, Ensheng Shi, Xilin Liu, Yuchi Ma, Guanbin Li

llms agents

arXiv AI

Jul 22

Towards an Automated Test of LLM Security Knowledge

arXiv:2607. 18496v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks.

By Shufan Chai, Liangliang Sun, Jessica Staddon

llms benchmarks

Get the daily briefing