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...
Fan Zhang, Yan-Kai Chen, Zhuo-Han Xie et al.· 13 citations· ⚡1
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.
Eduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia et al.· 0 citations
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.
Alexey Zakharov, Kemal Oksuz, P. Dokania· 0 citations
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...
Amit Jadhav, Shaurya Beriwala, Beomjin Kim· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
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...
Jia-Xing Li, Lei Song, Rui Dong et al.· 0 citations
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.
Egor Romanyukov, Timofey Novikov, Timur Shokarov et al.· 0 citations
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.
Zhi-Heng Hu, Yi-Xun Wei, Jian Zhou et al.· 0 citations
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.
SafeLoop is introduced, a non-invasive external wrapper that adds hazard prediction and rollback-based recovery to a VLA model without changing its parameters, and achieves a stronger overall safety-success trade-off than alternative methods.
Zeyuan Lou, Tian-Ran Zhang, Xin-Quan Yue et al.· 0 citations
Recursive invariants, a small statically typed domain-specific language (DSL) that formalizes UTXO validation and ledger extension, identifies the validation-time-evaluable one-step fragment, and proves the deduction system sound w.r.t. the three-valued semantics.
Shu-Yang Tang, Sherman S. M. Chow, Hong-Fei Fu et al.· Proceedings of the ACM on Pr...· 0 citations
