arXiv:2611.06280v1 Announce Type: new Abstract: Physics sensing in evolving environments requires reconstructing dense spatiotemporal fields from sparse…
From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+
arXiv:2611.06123v1 Announce Type: new Abstract: Alexa+ devices with screens display animated icons during conversations to visually reinforce what is…
CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution
arXiv:2611.06151v1 Announce Type: new Abstract: Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse…
Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web
arXiv:2611.06110v1 Announce Type: new Abstract: Online scam videos pose significant threats to individuals and society. Existing studies primarily focus…
ModalSearcher: Weaving Visual Evidence into Autonomous Cross-Modal Deep Search
arXiv:2611.06131v1 Announce Type: new Abstract: Static and incomplete parametric knowledge limits the performance of multimodal large language models on…
AutoStore Moves Into Pallet Robotics With Agreement to Buy Logiqs
AutoStore announced on November 5, 2026 that it had agreed to acquire Logiqs BV, a Netherlands-based developer of roaming pallet automated storage and…
SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving
arXiv:2611.06147v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving…
AI News Brief Hourly Summary 2026-11-05 11h : 11 posts
11 posts published in the last hour 09:38UniCompress: From Multi-LoRA Experts to One Compact Model for Edge Intelligence 09:37Which One Is Sounding? Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation 09:37From Waste to Discovery: Recycling High-Scored Unexposed Candidates in Taobao Feed…
UniCompress: From Multi-LoRA Experts to One Compact Model for Edge Intelligence
arXiv:2611.06075v1 Announce Type: new Abstract: Embodied and edge systems increasingly rely on vision-language models (VLMs) to support heterogeneous…
Which One Is Sounding? Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation
arXiv:2611.06074v1 Announce Type: new Abstract: Existing audio-visual segmentation methods mainly predict sound-related regions or category masks and…
From Waste to Discovery: Recycling High-Scored Unexposed Candidates in Taobao Feed Recommendation
arXiv:2611.05997v1 Announce Type: new Abstract: Helping users discover new interests is vital to the long-term health of industrial recommender systems,…
Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement
arXiv:2611.06049v1 Announce Type: new Abstract: Personal agents draw on past conversations to tailor their responses to each user. Their memory systems…
Reasoning-Trace Overflow in Code Generation: An Empirical Study of Explicit Reasoning Models
arXiv:2611.06095v1 Announce Type: new Abstract: Explicit reasoning can help language models generate code, but it also introduces a practical risk: the…
Routes of Reasoning: Reading and Reshaping Test-Time Compute in MoE Models
arXiv:2611.05919v1 Announce Type: new Abstract: Reasoning models allocate test-time compute across distinct behaviors such as planning, deriving, and…
CHARM+: Cross-Hardware Attention with Re-Merge Multistream Mechanism
arXiv:2611.05906v1 Announce Type: new Abstract: As sequence lengths continue to grow, distributed attention based on sequence parallel (e.g.,…
Autonomous agents for electricity-system planning
arXiv:2611.05911v1 Announce Type: new Abstract: Planning electricity systems requires repeated decisions that connect regional resources, investment,…
Split-KV: Efficient Context Parallelism for Training Diffusion Drafters
arXiv:2611.05926v1 Announce Type: new Abstract: Diffusion drafters accelerate speculative decoding by denoising multiple draft tokens in parallel. Their…
Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination
arXiv:2611.05953v1 Announce Type: new Abstract: Graphs play an increasingly important role in large language model (LLM) systems, supporting structural…