Large language models

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

31,367 stories · RSS feed

arXiv Machine Learning

Jun 5

RREDCoT: Segment-Level Reward Redistribution for Reasoning Models

arXiv:2606. 06475v1 Announce Type: new Abstract: Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning.

By Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger, Sepp Hochreiter

llms computer-vision reinforcement-learning fine-tuning

arXiv Machine Learning

Jun 5

End-to-End Subgraph Detection with GraphDETR

arXiv:2606. 06364v1 Announce Type: new Abstract: Subgraph detection seeks to identify whether and where instances of query patterns occur within a larger graph.

By Dexiong Chen, Till Hendrik Schulz, Karsten Borgwardt

llms computer-vision

arXiv Machine Learning

Jun 5

The Evaluation Blind Spot: A Stereological Theory of Benchmark Coverage for Large Language Models

arXiv:2606. 05169v1 Announce Type: new Abstract: We give a stereological theory of LLM benchmark coverage.

By Jason Z Wang

llms benchmarks

arXiv Machine Learning

Jun 5

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

arXiv:2606. 05781v1 Announce Type: new Abstract: Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead.

By Srinivasan Manoharan, Dilipkumar Nallusamy, Sachin Kumar, Haifeng Wu

llms fine-tuning safety

arXiv Machine Learning

Jun 5

Temporal Preference Concepts and their Functions in a Large Language Model

arXiv:2606. 05194v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading off near-term gains against long-term consequences, yet little is known about how they internally represent or resolve these tradeoffs.

By Ian Rios-Sialer, Shantanu Darveshi, Shuai Jiang, Avigya Paudel, Anastasiia Pronina, Ipshita Bandyopadhyay, Justin Shenk

llms safety

arXiv Machine Learning

Jun 5

LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, "Is Your VLM Smarter Than a 5th Grader?")

arXiv:2606. 05497v1 Announce Type: new Abstract: Given the inherently multimodal nature of human experience, vision-language models (VLMs) hold substantial promise for modeling human cognition as it grows and develops with experience.

By Alvin Wei Ming Tan, David Cardinal, Tania Lorido-Botran, Laura Bravo-Sanchez, Sunny Yu, Michael C. Frank

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 5

You Only Index Once: Cross-Layer Sparse Attention with Shared Routing

arXiv:2606. 06467v1 Announce Type: cross Abstract: Long-context inference in modern LLMs is increasingly constrained by decoding efficiency, especially in reasoning-heavy settings where models generate long intermediate chains of thought.

By Yutao Sun, Yanqi Zhang, Li Dong, Jianyong Wang, Furu Wei

llms efficiency benchmarks

arXiv Machine Learning

Jun 5

Q-GNN: Query-Conditioned Graph Neural Networks with Type Awareness for Knowledge Graph Completion

arXiv:2606. 05639v1 Announce Type: new Abstract: Knowledge Graph Completion (KGC) aims at predicting missing triplets from incomplete knowledge graphs, which is crucial for downstream applications.

By Dongxiao He, Ruqiong Zhang, Zhizhi Yu, Ling Ding, Di Jin, Guangquan Xu, Zhiyong Feng

llms benchmarks

arXiv Machine Learning

Jun 5

SpanNorm: Reconciling Training Stability and Performance in Deep Transformers

arXiv:2601. 22580v2 Announce Type: replace-cross Abstract: The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures.

By Chao Wang, Bei Li, Jiaqi Zhang, Xinyu Liu, Yuchun Fan, Linkun Lyu, Xin Chen, Jingang Wang, Tong Xiao, Peng Pei, Xunliang Cai

llms

arXiv Machine Learning

Jun 5

LLM Explainability with Counterfactual Chains and Causal Graphs

arXiv:2606. 05972v1 Announce Type: new Abstract: Causal graphs provide a high-level language for making mechanisms transparent.

By Nirit Nussbaum-Hoffer, Nitay Calderon, Liat Ein-Dor, Roi Reichart

llms nlp

arXiv Machine Learning

Jun 5

Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs

arXiv:2602. 09574v2 Announce Type: replace-cross Abstract: Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment often imposes a fixed per-query token budget that varies across settings.

By Sora Miyamoto, Daisuke Oba, Naoaki Okazaki

llms benchmarks

arXiv Machine Learning

Jun 5

Learned Subspace Compression for Communication-Efficient Pipeline Parallelism

arXiv:2606. 05484v1 Announce Type: new Abstract: Pipeline parallelism enables training of large language models that exceed single-device memory, yet inter-stage activation communication becomes the dominant bottleneck when trained on low-bandwidth networks.

By Paul Janson, Edouard Oyallon, Eugene Belilovsky

llms rag efficiency

arXiv Machine Learning

Jun 5

TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation

arXiv:2606. 06133v1 Announce Type: cross Abstract: TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols.

By Eric Spencer, Arslan Bisharat, Brian Ortiz, Khushboo Bhadauria, TaiNing Wang, George K. Thiruvathukal, Konstantin Laufer, Mohammed Abuhamad

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 5

Algebraic Diversity: Group-Theoretic Spectral Estimation from Single Observations

arXiv:2604. 03634v5 Announce Type: replace Abstract: We establish that temporal averaging over multiple observations is the degenerate case of algebraic group action with the trivial group $G=\{e\}$.

By Mitchell A. Thornton

llms rag

arXiv Machine Learning

Jun 5

T-SAR-JEPA: Self-Supervised Temporal Anomaly Detection in SAR Amplitude Stacks via Latent Prediction

arXiv:2606. 05700v1 Announce Type: cross Abstract: We present T-SAR-JEPA, a self-supervised framework for temporal anomaly detection in SAR amplitude stacks via latent prediction.

By Kerod Woldesenbet, Abem Woldesenbet

llms

arXiv Machine Learning

Jun 5

GRAMformer: Any-Order Modality Interactions via Volumetric Multimodal Cross-Attention

arXiv:2606. 06249v1 Announce Type: cross Abstract: Transformer-based multimodal models rely on attention mechanisms to integrate information across heterogeneous modalities.

By Giordano Cicchetti, Eleonora Grassucci, Danilo Comminiello

llms multimodal

arXiv Machine Learning

Jun 5

On the training of physics-informed neural operators for solving parametric partial differential equations

arXiv:2606. 06164v1 Announce Type: new Abstract: Physics-informed neural operators (PINOs) aim to learn solution operators for partial differential equations by using the governing physics as supervision, rather than relying solely on paired input-output simulation data.

By Nanxi Chen, Chuanjie Cui, Airong Chen, Sifan Wang, Rujin Ma

llms computer-vision benchmarks

arXiv Machine Learning

Jun 5

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

arXiv:2606. 06333v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional.

By Seyed Arshan Dalili, Mehrdad Mahdavi

llms efficiency safety

arXiv Machine Learning

Jun 5

On Advantage Estimates for Max@K Policy Gradients

arXiv:2606. 06080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficult.

By Shota Takashiro, Soichiro Nishimori, Paavo Parmas, Yongmin Kim, Kohsei Matsutani, Gouki Minegishi, Yusuke Iwasawa, Takeshi Kojima, Yutaka Matsuo

llms reinforcement-learning

arXiv Machine Learning

Jun 5

AlloGen: Conformation-Selective Binder Generation with Differential State Scoring

arXiv:2606. 05474v1 Announce Type: cross Abstract: Protein binder design has largely optimized for affinity alone, leaving conformational selectivity unaddressed: for allosteric targets such as kinases, nuclear receptors, and GPCRs, a binder that engages both active and inactive states provides no functional specificity regardless of how tightly it binds.

By Hanqun Cao, Zachary Quinn, Aastha Pal, Sumi Kimura, Jingjie Zhang, Pheng Ann Heng, Pranam Chatterjee

llms benchmarks

Get the daily briefing