arXiv:2610.14777v1 Announce Type: new Abstract: LLM-powered data analytics aims to translate natural language instructions into executable analytical…
Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB
Z.ai’s GLM-Legal is a legal AI model built on GLM-5.3-Flash. It scores 19.2% all-pass on Harvey’s Legal Agent Benchmark, nearly 3x its base, at $0.15 per…
How Should a Camera-First AI Agent Work?
arXiv:2610.14772v2 Announce Type: new Abstract: Camera-first agents must act on the visual world as it unfolds. We argue that the central obstacle for…
AI News Brief Hourly Summary 2026-10-15 11h : 11 posts
11 posts published in the last hour 08:36SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability 08:36Relational Semantic Grounding for Test-Time Discovery 08:36Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems 08:35MHWA: Multi-timescale Hierarchical World-Action Model 08:35Equal-information evaluation…
SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability
arXiv:2610.14745v1 Announce Type: new Abstract: Extreme low-bit weight-only quantization is an effective approach to reducing the deployment costs of…
Relational Semantic Grounding for Test-Time Discovery
arXiv:2610.14721v1 Announce Type: new Abstract: Test-Time Discovery (TTD) aims to recognize known classes and detect novel ones from a continuous…
Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems
arXiv:2610.14736v1 Announce Type: new Abstract: Optimization by PROmpting (OPRO) directly leverages Large Language Models (LLMs) to generate candidate…
MHWA: Multi-timescale Hierarchical World-Action Model
arXiv:2610.14727v1 Announce Type: new Abstract: Autoregressive world models have emerged as a powerful paradigm for sample efficient decision making, yet…
Equal-information evaluation of credit assignment in modular financial reinforcement learning
arXiv:2610.14750v1 Announce Type: new Abstract: Credit assignment in modular financial reinforcement learning is difficult to evaluate because an…
How to Build a Benchmark That Actually Measures Taste
arXiv:2610.14707v2 Announce Type: new Abstract: Expert-aligned “taste” benchmarks should reward craft judgment, not the ability to game the test. We…
DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents
arXiv:2610.14700v1 Announce Type: new Abstract: Most text-to-SQL benchmarks provide the target database. In a large data catalog, however, choosing the…
A Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition
arXiv:2610.14680v1 Announce Type: new Abstract: Sign Language Recognition (SLR) presents complex challenges due to variable signing speeds and spatial…
Joint Discrete and SE(3) Diffusion for Protein Interface Design
arXiv:2610.14699v1 Announce Type: new Abstract: The design of high-affinity, target-specific protein binders is central to the development of modern…
AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation
arXiv:2610.14693v1 Announce Type: new Abstract: Explicit point correspondence is attractive for adapting video generators: it describes how visible…
AI News Brief Hourly Summary 2026-10-15 10h : 14 posts
14 posts published in the last hour 07:34AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech 07:34PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents 07:34TIER IV Funds New Autoware Research Hub at Munich University 07:34RASSG: Repair-Aware Semantic Survival Gating for…
AegisVox: Factorized Privacy and Clinical Preservation for Long-Form Speech
arXiv:2610.14643v1 Announce Type: new Abstract: Clinical speech reveals identity through both spoken identifiers and voice, yet its pauses, delivery, and…
PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents
arXiv:2610.14636v1 Announce Type: new Abstract: Terminal rewards make multi-turn agents trainable without step-level annotations, but group-relative…
TIER IV Funds New Autoware Research Hub at Munich University
TIER IV and the Technical University of Munich announced on October 15, 2026 that they have established the TUM Autoware Research Center by TIER IV…