YouZum

ニュース

ニュース

Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective

arXiv:2510.08800v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated advanced reasoning capabilities...

BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning

arXiv:2510.27623v3 Announce Type: replace-cross Abstract: Recent advances in Vision-Language Models (VLMs) have propelled embodied agents...

Batch-Max: Higher LLM Throughput using Larger Batch Sizes and KV Cache Compression

arXiv:2412.05693v3 Announce Type: replace Abstract: Several works have developed eviction policies to remove key-value (KV)...

Base Models Beat Aligned Models at Randomness and Creativity

arXiv:2505.00047v2 Announce Type: replace Abstract: Alignment has quickly become a default ingredient in LLM development...

BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali

arXiv:2601.01778v1 Announce Type: new Abstract: Despite its widespread use, Bengali lacks a robust automated International...

Aya Vision: Advancing the Frontier of Multilingual Multimodality

arXiv:2505.08751v1 Announce Type: new Abstract: Building multimodal language models is fundamentally challenging: it requires aligning...

AWARE, Beyond Sentence Boundaries: A Contextual Transformer Framework for Identifying Cultural Capital in STEM Narratives

arXiv:2510.04983v3 Announce Type: replace Abstract: Identifying cultural capital (CC) themes in student reflections can offer...

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition

arXiv:2509.07555v1 Announce Type: new Abstract: In a rapidly evolving world where information updates swiftly, knowledge...

AutoSpec: An Agentic Framework for Automatically Drafting Patent Specification

arXiv:2509.19640v1 Announce Type: new Abstract: Patents play a critical role in driving technological innovation by...

AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists

arXiv:2506.08140v1 Announce Type: cross Abstract: Despite long-standing efforts in accelerating scientific discovery with AI, building...

We use cookies to improve your experience and performance on our website. You can learn more at プライバシーポリシー and manage your privacy settings by clicking Settings.

Privacy Preferences

You can choose your cookie settings by turning on/off each type of cookie as you wish, except for essential cookies.

Allow All
Manage Consent Preferences
  • Always Active

Save
ja