Topics

10 topics, by number of papers. Each paper has one.

10 of 10 topics

Topic	Papers	Last 12 months	Latest
Foundation models9 papers · Technical reports for new model families.	9	1	Jul 2026
Alignment and safety7 papers · Making models follow intent and resist misuse: RLHF, preferences, jailbreaks, deception, hallucination.	7	0	Sep 2025
Training and scaling5 papers · Scaling laws, fine-tuning, distributed training and optimisation.	5	0	May 2024
Inference and efficiency4 papers · Serving, attention kernels, KV caches, quantisation: the cost of running models.	4	1	Sep 2026
Multimodal and robotics4 papers · Vision, video, audio, world models and robot control.	4	3	Aug 2026
Agents and evaluation3 papers · Agents, harnesses, benchmarks and how to measure them.	3	3	Sep 2026
Architectures3 papers · The shapes of models: Transformers, state space models, mixture of experts.	3	1	Aug 2026
Reasoning2 papers · Step-by-step thinking, reinforcement learning for reasoning, math and logic.	2	0	Jan 2025
Retrieval and data2 papers · Embeddings, RAG, search over documents and the data models learn from.	2	0	May 2024
Applied AI1 paper · Models put to work in a domain: education, science, medicine, code.	1	1	Sep 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

Topics

New papers by email