arXiv:2611.17338·arXiv Artificial Intelligence (cs.AI)·3 hours ago
Score: 79/100 · Citations: 0When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors
Authors: Samarth Vinayaka
AI Synthesis: The available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three
Read Paper Abstract & Impact Analysis
arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity...
Why it matters: This development in LLMs provides actionable signal for engineering, research, and policy teams monitoring arXiv Artificial Intelligence (cs.AI).
arXiv:2611.17339·arXiv Artificial Intelligence (cs.AI)·3 hours ago
Score: 78/100 · Citations: 0Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs
Authors: Shubhra Mittal, Gaurav Naresh Mittal
AI Synthesis: The available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The
Read Paper Abstract & Impact Analysis
arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The small models practitioners actually ship...
Why it matters: This development in LLMs provides actionable signal for engineering, research, and policy teams monitoring arXiv Artificial Intelligence (cs.AI).
arXiv:2611.17340·arXiv Artificial Intelligence (cs.AI)·3 hours ago
Score: 78/100 · Citations: 0LoRAWeaver: Directional Adapter Routing in LoRA Representation Space
Authors: Inish Melroy D Souza, Tom Jackson, Vitor Castro, Rebecca Higginson, Andrea Soltoggio
AI Synthesis: The available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-
Read Paper Abstract & Impact Analysis
arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool...
Why it matters: This development in LLMs provides actionable signal for engineering, research, and policy teams monitoring arXiv Artificial Intelligence (cs.AI).
arXiv:2611.17341·arXiv Artificial Intelligence (cs.AI)·3 hours ago
Score: 78/100 · Citations: 0Tabular Population Priors as Structured Retrieval for EHR Medication Set Prediction
Authors: Animesh Agarwal, Meysam Ghaffari, Nina Fatehi, Carlos Morato
AI Synthesis: The available reporting indicates from arXiv Artificial Intelligence (cs.AI) that arXiv:2611.17341v1 Announce Type: new Abstract: Medication prediction from electronic health records is a fixed vocabulary structured prediction problem, yet recent clinical RAG systems often treat it like open ended case based reasoning:
Read Paper Abstract & Impact Analysis
arXiv:2611.17341v1 Announce Type: new Abstract: Medication prediction from electronic health records is a fixed vocabulary structured prediction problem, yet recent clinical RAG systems often treat it like open ended case based reasoning: retrieve similar patient admissions and...
Why it matters: This development in Clinical AI provides actionable signal for engineering, research, and policy teams monitoring arXiv Artificial Intelligence (cs.AI).
arXiv:2611.21339·Hugging Face Daily Papers·1 day ago
Score: 73/100 · Citations: 0MovieRoll: A Systematic Framework for Rolling Out Long-Form Videos
Authors: Hugging Face Daily Papers
AI Synthesis: The available reporting indicates from Hugging Face Daily Papers that Streaming video generation must sustain quality beyond the training horizon while handling self-generated history and growing cache costs. To address these challenges, we present MovieRoll, a base-to-distilled framework that connects streaming fine-t
Read Paper Abstract & Impact Analysis
Streaming video generation must sustain quality beyond the training horizon while handling self-generated history and growing cache costs. To address these challenges, we present MovieRoll, a base-to-distilled framework that connects streaming fine-tuning, long-rollout...
Why it matters: This development in LLMs provides actionable signal for engineering, research, and policy teams monitoring Hugging Face Daily Papers.
arXiv:2611.21003·Hugging Face Daily Papers·1 day ago
Score: 73/100 · Citations: 0K2-Horizon: A Frontier Fleet of Open Source Language Models
Authors: Hugging Face Daily Papers
AI Synthesis: The available reporting indicates from Hugging Face Daily Papers that We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software engineering, deep research, office automation, and be
Read Paper Abstract & Impact Analysis
We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software engineering, deep research, office automation, and beyond. The models lead or are...
Why it matters: This development in AI Agents provides actionable signal for engineering, research, and policy teams monitoring Hugging Face Daily Papers.
arXiv:2611.19937·Hugging Face Daily Papers·2 days ago
Score: 70/100 · Citations: 0AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data
Authors: Hugging Face Daily Papers
AI Synthesis: The available reporting indicates from Hugging Face Daily Papers that Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportu
Read Paper Abstract & Impact Analysis
Real-world portfolio management requires converting noisy market observations into coordinated, simultaneous allocations across multiple assets under shared capital constraints. Advances in forecasting models and alpha discovery help identify opportunities. However, traditional...
Why it matters: This development in Research provides actionable signal for engineering, research, and policy teams monitoring Hugging Face Daily Papers.
arXiv:2611.20254·Hugging Face Daily Papers·2 days ago
Score: 70/100 · Citations: 0VoxMel TTS Technical Report
Authors: Hugging Face Daily Papers
AI Synthesis: The available reporting indicates from Hugging Face Daily Papers that Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to
Read Paper Abstract & Impact Analysis
Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable,...
Why it matters: This development in Speech provides actionable signal for engineering, research, and policy teams monitoring Hugging Face Daily Papers.