#multimodal
#multimodal 16 items · All topics →
arXiv cs.AI · 13:00 Score 80 This work lets LLM agents negotiate and transact autonomously in multi-agent commerce, combining dialogue with multimodal product information.
Why this: Covers model and LLM · Relevant to this topic
arXiv cs.AI · 13:00 Score 75 This benchmark tests web agents on realistic cross-application browser tasks spanning heterogeneous interfaces and multimodal inputs.
Why this: Covers model and multimodal · Relevant to this topic
arXiv cs.AI · 13:00 Score 75 This work quantifies uncertainty for multimodal LLMs with an incoherence-adjusted semantic volume, so plausible but wrong outputs are not mistaken for reliable ones.
Why this: Covers model and LLM · Relevant to this topic
arXiv cs.AI · 13:00 Score 75 This work lets GUI agents ground interface elements purely visually, without metadata, eliminating hallucination-prone localization.
Why this: Covers model and LLM · Relevant to this topic
arXiv cs.AI · 13:00 Score 70 Multimodal agentic coding needs to see the visual results of generated code, and Vision-as-a-Tool turns visual ability into a tool so agents can observe and evaluate their own artifacts.
Why this: Covers multimodal and Agent · Relevant to this topic
arXiv cs.AI · 13:00 Score 70 This distributed asynchronous RL framework keeps vision-language-action model training apace with the rapid evolution of embodied AI.
Why this: Covers model and multimodal · Relevant to this topic
arXiv cs.AI · 13:00 Score 65 When IoT time series meet external text like expert reports, this benchmark diagnoses how forecasting models behave when those signals agree, conflict, or go unspecified.
Why this: Covers multimodal and benchmark · Relevant to this topic
arXiv cs.AI · 13:00 Score 65 This model lets service robots identify users from their preferences and past interactions under varying observation conditions.
Why this: Covers model and multimodal · Relevant to this topic
arXiv cs.AI · 13:00 Score 65 This audit examines whether the topographic organization inside TRIBE v2 holds up when it predicts fMRI responses across the cortex.
Why this: Covers model and multimodal · Relevant to this topic
arXiv cs.AI · 13:00 Score 65 This work lets multimodal LLMs sequentially acquire new capabilities without catastrophic forgetting, consolidating and preserving MoE experts.
Why this: Covers model and multimodal · Relevant to this topic
arXiv cs.AI · 13:00 Score 65 This work teaches vision-language models to self-verify from multiple perspectives and know when to rethink.
Why this: Covers model and multimodal · Relevant to this topic
arXiv cs.AI · 13:00 Score 65 CARE-Drive improves ego-trajectory planning in end-to-end autonomous driving with coupled alternating refinement for vision-language-action models.
Why this: Covers model and multimodal · Relevant to this topic
StoneTech's new multimodal model service makes AI video 2.48x faster without sacrificing quality.
Why this: Covers model and multimodal · Relevant to this topic
Google AI Blog · 02:00 Score 75 Meet the Gemini Decisions API, powered by the Gemini Decision model for fast, calibrated multimodal decisions.
Why this: Official source · Covers model and Gemini
Mistral News · 20:00 Score 65 Mistral has opened the weights of its 1T-parameter multimodal model Large 4 (Le Chonk), the strongest open-weight coding model to date, trained in Europe.
Why this: Official source · Covers model and multimodal
Hugging Face Blog · 01:16 Score 65 LiquidAI's LFM3 helps developers build specialized multimodal models for specific tasks.
Why this: Official source · Covers model and multimodal