Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile devices also arises, such as the AI assistant software. Some efforts try to migrate VLMs to edge devices to expand their application scope. Simplifying the model structure is a common method, but as the model shrinks, th
We propose COLLAB-REC, a multi-agent framework designed to counteract popularity bias and improve diversity in tourism recommendations. In our setup, three LLM-based agents(Personalization, Popularity, and Sustainability) generate city suggestions from different perspectives. A non-LLM moderator then merges and refines these proposals through iterative constrained refinement, ensuring that each ag
The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice. Rather than encoding all procedural knowledge within model weights, agent skills -- composable packages of instructions, code, and resources that agents load on demand -- enable dynamic capability extension without retraining. It is f
Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes FoundCAC, a universal foundational framework that resolves two challenges hindering the generalization of existing pipelines:
Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states. Existing approaches, including retrieval-augmented generation and explicit memory systems, primarily operate at the fact level, making it difficult to distill stable preferences and deep user
Money is concentrating in infrastructure and frontier AI, with one outsized round dwarfing the rest of the cycle. A smaller application-layer check shows early-stage capital still backing vertical products.
Money is concentrating in infrastructure and frontier AI, with one outsized round dwarfing the rest of the cycle. A smaller application-layer check shows early-stage capital still backing vertical products.
Money is concentrating in infrastructure and frontier AI, with one outsized round dwarfing the rest of the cycle. A smaller application-layer check shows early-stage capital still backing vertical products.
Named moves are sparse, but the desk still matters because leadership changes can reweight a lab or product group quickly. One senior hire and two departures suggest both consolidation and churn around AI teams.
Named moves are sparse, but the desk still matters because leadership changes can reweight a lab or product group quickly. One senior hire and two departures suggest both consolidation and churn around AI teams.
Named moves are sparse, but the desk still matters because leadership changes can reweight a lab or product group quickly. One senior hire and two departures suggest both consolidation and churn around AI teams.
Benchmark activity is limited to a single model family across reasoning and knowledge tests. The significance is less a leaderboard shake-up than a fresh measurement baseline for a widely tracked open-weight system.
Benchmark activity is limited to a single model family across reasoning and knowledge tests. The significance is less a leaderboard shake-up than a fresh measurement baseline for a widely tracked open-weight system.
Benchmark activity is limited to a single model family across reasoning and knowledge tests. The significance is less a leaderboard shake-up than a fresh measurement baseline for a widely tracked open-weight system.