ROBOMARKET
Stay Informed
Daily coverage from 6044 trusted sources — robotics, AI agents, and industry analysis for the GCC.
Last Updated: 02:00 AM (1h ago)
Auto-refresh every 2 hours
Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment
arXiv:2609.19209v1 Announce Type: new Abstract: Generative query suggestion aims to enhance user engagement by anticipating user intents and recommending relevant follow-up queries. A central challenge is to generate slates whose individual queries are useful while the slate covers distinct intents. We propose an Intent-Driven Query Suggestion Framework with dual-stage optimization. First, intent-aware diversity modeling constructs intent-aligned supervised fine-tuning (SFT) data and uses an Intent-Aware Diversity Reward to optimize intent coverage. Second, query-level credit assignment routes individual quality signals to the corresponding query tokens while sharing a slate-level diversity signal across the slate. Experiments on a large-scale production dataset, including online A/B testing and offline evaluation, show improvements in click-through rate, query quality, and intent coverage.
AthenaZero: A low-inertia, bimanual robot for dynamic manipulation
arXiv:2609.19194v1 Announce Type: new Abstract: AthenaZero is a bimanual manipulator designed to minimize inertia without compromising control authority. By utilizing quasi-direct drive actuation and transmission remotization techniques, the system achieves an effective endpoint mass comparable to that of a human---about an order of magnitude less than conventional robot manipulators. This characteristic, combined with its inherent torque transparency, makes AthenaZero exceptionally well-suited for dynamic manipulation. We describe the methodology} that led to this design and demonstrate the robot's capabilities on three baseball-inspired tasks: throwing, catching, and batting, which showcase complex interactions on human-comparable timescales where milliseconds matter. AthenaZero was capable of throwing at speeds in excess of 30 m/s, with catching and batting at speeds in excess of 14 m/s over a short 7.3 m distance. Batting practice and a game of catch were subsequently performed in
Layer-wise Curriculum Learning for Efficient LLM Compression
arXiv:2609.19213v1 Announce Type: new Abstract: In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from the teacher model to the student model, utilizing a curriculum learning approach that begins with easier optimization tasks and progressively tackles harder ones. In order to adopt the layer-wise learning in LLM compression, we partition the whole model into multiple segments consisting of layers, thereby enabling more computationally efficient knowledge transfer for LLMs. Based on our theoretical analysis of cumulative error phenomenon, layer-wise curriculum learning accelerates convergence while stabilizing the knowledge transfer process. In addition, we present a feature caching method with a multi-threading strategy to efficiently address feature misalignment across layers, maximizing GPU utilization. Consequently, our method exhibits advanced model compression performance, as well as hi
DITTO: Dexterous Interface for Transparent TeleOperation
arXiv:2609.19196v1 Announce Type: new Abstract: Collecting data for manipulation with high-DOF hands is challenging, as interfaces must capture rich hand motion while rendering the contact interactions essential for precise manipulation. Existing data collection approaches face a trade-off: teleoperation ensures deployment consistency but lacks force feedback, while handheld (in-the-wild) systems provide natural force transparency but introduce a visual embodiment gap at deployment. We present DITTO, a Dexterous Interface for Transparent TeleOperation, which resolves this through the anatomically informed co-design of a dexterous 7-DOF robotic hand and a kinematically equivalent motorized exoskeleton. A 1-to-1 actuator mapping between the exoskeleton and robotic hand enables handheld (in-the-wild) data collection and bilateral teleoperation with joint-level force feedback unified in a single platform. We demonstrate that the DITTO exoskeleton spans the operator's natural index-to-thumb
A Startup Tripled Its Valuation in 5 Months. Here’s What That Says About the Future of Coding.
In April, Factory was worth $1.5 billion. Five months later, it s worth $5 billion. No new product launch, no viral moment just Continue reading on Medium »
The questions to resolve before making a synthetic voice
A synthetic voice can make a new script sound as though a particular person read it. That is what makes the technology useful in some Continue reading on Medium »
Waymo says Singapore will be its next international robotaxi city
Waymo Ojai fully autonomous ride-hailing vehicle travels along a city street, San Francisco, California, August 20, 2026. (Photo by Smith Collection/Gado/Getty Images) | Gado via Getty Images Waymo says it will launch a robotaxi service in Singapore in 2028, as the Alphabet-owned company continues to eye overseas markets for expansion. Waymo's vehicles will begin arriving in Singapore in "the coming months," the company says, in preparation of mapping and autonomous testing with human safety drivers behind the wheel in 2027. Waymo says it is "working toward offering fully autonomous ride-hailing to the public" by 2028. Waymo will need approval from Singapore's Land Transport Authority (LTA) before it can begin accepting passengers. The city-state requires all autonomous vehicles to undergo a safety assessment conducted at the … Read the full story at The Verge.
How to Access Multiple AI Models With One API Key
A practical guide to unified AI APIs, model switching, and production-safe routingContinue reading on Medium »
Building a Custom LLM, Part 1:Can We Build the Strongest LLM from Just 10 Million Words?
Building a custom language model with BabyLM s data budget and benchmark tasksContinue reading on Medium »
Khosla-backed Mazama Energy just raised $135M to drill deeper into super-hot-rock geothermal
Geothermal startup Mazama is drilling three miles underground to tap superhot rock, with one well capable of generating 15 MW of electricity 24/7.
LLM API Pricing Guide 2026: What 1M Tokens Really Cost After the Price Cuts
Disclosure: This article was created with AI assistance AI tools helped with research, drafting, and fact-checking. Affiliate disclosure Continue reading on Medium »
Frankenstein Was Never About the Monster. It’s About Us.
Should we be afraid of the Singularity in Artificial Intelligence?Continue reading on Medium »