Category
2,897 papers
Mizar, a 159.3M-parameter ALM, is introduced, a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM that surpasses the previous best-performing ALM below 200M parameters on all three benchmarks.
As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has become a critical challenge. While recent work has moved beyond single-turn evaluation toward multi-turn paradigms, key limitations persist: step-level methods treat ac...
Jev has the lowest cost and median response time among the evaluated configurations, while hosted language models achieve higher baseline accuracy and Rankings by baseline accuracy differ from rankings by correctness across every condition and repeat, although small differences in the latter do not establish a general...
This work isolates SLM graph reasoning from navigation and traceability capability by employing the THESEUS navigation and traceability framework and using frozen, off-the-shelf SLMs as local action policies, and results motivate evaluating SLM graph reasoning beyond endpoint accuracy alone.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A three-stage pipeline that transforms abundant unlabelled observation-trajectory pairs into a substrate for language-conditioned control and achieves a Driving Score of 87.98 and a Success Rate of 70.46%, matching or surpassing fully supervised baselines on the closed-loop Bench2Drive benchmark.
Vision-language models (VLMs) are deployed as zero-shot judges of image aesthetics, and panels of several models are recommended, on thin evidence, as the way to make such judges reliable. On two human-rated datasets, EVA and PARA, we find that a panel of holistic judges never significantly beats its best member, wheth...
This work introduces MemeCF, a cue-focused benchmark of 9,895 memes across harm, hate, and sarcasm, with annotations identifying the modality and rationale of the pivotal evidence.
This paper proposes FRESH, a Failure-aware Retrieval framework over Experience-Structured Heterogeneous graphs, which transforms historical successes and failures into structured external experience for tool-using agents and consistently improves task success and tool-use reliability over no-memory agents and represent...
Direct transfer of Step Law systematically overestimates the optimal learning rate: the median ratio eta_SL / eta* is approximately 4.0x, with a range of 2.4x to 6.6x.
FWBench enables reproducible evaluation of how language models select and use time-series forecasts to make decisions under cost constraints.
KV-Invariant Transformer Expansion (KITE) is introduced, a scaling paradigm that trains the model from a smaller size to a larger size (i.e., saving training costs via upcycling), while places newly added parameters in regions that do not affect attention KV.
A comprehensive English–Norwegian framework that unifies multi-class, multi-label, and multi-task learning for hate speech detection while embedding fairness, transparency, and accountability is proposed.
Earth AI
A Blog post by Ai2 on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
