Latest AI/ML News
2637 articles · 🧠 Research
arXiv:2608.07531v2 Announce Type: replace Abstract: Search-augmented language agents should retrieve external information only when necessary and grou…
arXiv:2608.04772v2 Announce Type: replace Abstract: Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation…
arXiv:2607.26654v3 Announce Type: replace Abstract: Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whe…
arXiv:2607.15209v2 Announce Type: replace Abstract: Multilingual pre-trained language models such as XLM-R perform well for major languages but strugg…
arXiv:2607.08642v3 Announce Type: replace Abstract: Speculative decoding accelerates LLM inference by drafting tokens and verifying them in parallel.…
arXiv:2607.04728v2 Announce Type: replace Abstract: Reinforcement learning (RL) post-training for large language models (LLMs) follows a efficient par…
arXiv:2606.23671v4 Announce Type: replace Abstract: Prior work shows that large language models (LLMs) exhibit introspective capability on benign task…
arXiv:2606.21802v2 Announce Type: replace Abstract: Standard tokenwise diffusion LMs keep training corruption and inference commitment at token granul…
arXiv:2605.31281v2 Announce Type: replace Abstract: As wind turbine fleets age, data-driven reliability engineering and maintenance optimisation are e…
arXiv:2605.24930v2 Announce Type: replace Abstract: Transformer-based LLMs achieve strong results on many language tasks; however, long inputs remain…
arXiv:2605.17443v3 Announce Type: replace Abstract: We analyze how automatic speech recognition (ASR) errors propagate through ASR--LLM cascades in Ko…
arXiv:2605.07725v3 Announce Type: replace Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability…
arXiv:2605.07507v2 Announce Type: replace Abstract: The rapid growth of academic publications has created a need for tools that extract structured kno…
arXiv:2604.20817v2 Announce Type: replace Abstract: Language models trained on natural text learn to represent numbers using periodic features with do…
arXiv:2604.06474v2 Announce Type: replace Abstract: Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-…
arXiv:2604.06416v2 Announce Type: replace Abstract: Although LLM context lengths have grown, there is evidence that their ability to integrate informa…
arXiv:2603.30025v3 Announce Type: replace Abstract: Automated fact-checking pipelines typically begin with a filtering stage that decides which claims…
arXiv:2603.24472v4 Announce Type: replace Abstract: Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving per…
arXiv:2603.23047v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) fine-tuning has shown substantial improvements over vanilla R…
arXiv:2603.09872v2 Announce Type: replace Abstract: Recent work has found that contemporary language models such as transformers can become so good at…