arXiv:2611.05072v1 Announce Type: cross Abstract: Although existing candidate trajectory evaluators have substantially improved end-to-end planning…
Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action
arXiv:2611.05058v1 Announce Type: cross Abstract: Recent multimodal language models can reason directly about robot scenes, but it is unclear whether they…
GeoFaham: Domain-Specialized Multi-Agent Geospatial Analytics for Disaster Response
arXiv:2611.04977v1 Announce Type: cross Abstract: Real-world geospatial decision support requires more than single-step retrieval or code generation.…
Rethinking GA2Ms: performance and out-of-distribution generalisation
arXiv:2611.05012v1 Announce Type: cross Abstract: Generalised Additive Models (GAMs) are a cornerstone of interpretable machine learning, offering…
Learned Smartphone ISP on Mobile GPUs: Mobile AI 2026 Challenge Report
arXiv:2611.05008v1 Announce Type: cross Abstract: With the increasing importance of mobile camera quality in modern smartphones, growing attention has…
RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report
arXiv:2611.05024v1 Announce Type: cross Abstract: On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos…
LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation
arXiv:2611.04974v1 Announce Type: cross Abstract: We investigate the automated generation of executable robot reinforcement learning (RL) policies from…
AI News Brief Hourly Summary 2026-11-05 05h : 12 posts
12 posts published in the last hour 03:33Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation? 03:32Fault-tolerant shallow recurrent decoders for sparse sensing with missing sensor measurements 03:32VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents 03:32Who is the Pronoun Pro?…
Shuffled OPSD: When Semantic Consistency Hurts On-Policy Self-Distillation?
arXiv:2611.04958v1 Announce Type: cross Abstract: Knowledge distillation improves a student model’s reasoning ability through supervision from a teacher.…
Fault-tolerant shallow recurrent decoders for sparse sensing with missing sensor measurements
arXiv:2611.04893v1 Announce Type: cross Abstract: Real-world sensing systems are inherently imperfect: sensors may fail, intermittently disconnect,…
VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents
arXiv:2611.04894v1 Announce Type: cross Abstract: Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some…
Who is the Pronoun Pro? Comparing LLMs and Humans at Number-Disambiguation of ‘they’
arXiv:2611.04968v1 Announce Type: cross Abstract: This study evaluates whether large language models (LLMs) can reliably replace or complement human…
One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough
arXiv:2611.04867v1 Announce Type: cross Abstract: The value of memory lies not only in recall but in using it to provide appropriate assistance. Recent…
UniFlow: Unified Multi-Scale Flow Matching for Time Series Generation
arXiv:2611.04825v1 Announce Type: cross Abstract: Real-world time series exhibit complex dynamics across multiple temporal resolutions, yet effectively…
ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement
arXiv:2611.04787v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective approach for improving…
Density-Aware Reward Scaling: A Reinforcement Learning Framework for Reward-Proportional Sampling
arXiv:2611.04792v1 Announce Type: cross Abstract: Reinforcement learning objectives that maximize expected return can concentrate probability mass on a…
Found by Search, Broken by a Shortcut: Transfer and Tampering of Searched Intrinsic Rewards
arXiv:2611.04838v1 Announce Type: cross Abstract: Can a search over innate drives find intrinsic rewards that help a reinforcement-learning agent learn,…
OpenAI’s Enterprise Sales Take Majority as Brockman Sees IPO Readiness
Reuters reported on November 5, 2026 that OpenAI President Greg Brockman said enterprise sales now generate the majority of the company’s revenue.…