arXiv:2609.09081v1 Announce Type: new Abstract: Mid-training, the stage between pre-training and alignment, is where a model’s per-domain data composition…
Tag: AI
PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving
arXiv:2609.08965v1 Announce Type: new Abstract: Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic…
SkillAdam: Stable and Efficient Skill Evolution for Agents
arXiv:2609.08944v1 Announce Type: new Abstract: Agent skills provide a lightweight way to equip frozen language-model agents with domain knowledge and…
API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
arXiv:2609.08861v1 Announce Type: new Abstract: Benchmark scores are a central currency in model releases: they inform purchasing decisions, shape public…
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
arXiv:2609.08966v1 Announce Type: new Abstract: Language-model checkpoints are commonly selected by pretraining loss or benchmark scores, assuming that…
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
arXiv:2609.08832v1 Announce Type: new Abstract: Large language model (LLM)-powered agents can be accurate on average yet unreliable in production, a…
GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data
arXiv:2609.08719v1 Announce Type: new Abstract: Automated alpha factor discovery searches symbolic trading signals from price-volume panels and order-book…
Mark Wahlberg is coming to TechCrunch Disrupt 2026, and he wants to talk about your work, not his
Mark Wahlberg joins Bruce K. Lee at Disrupt to discuss investing, entrepreneurship, healthcare, wellness and building businesses.
NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100
NVIDIA has detailed BioNeMo Inference Runtime (BioIR), a Python library that accelerates biomolecular structure-prediction models on NVIDIA GPUs while…
CLAMP: Constrained Decoding for Vision-Language Embodied Planning
arXiv:2609.08602v1 Announce Type: new Abstract: Embodied planning increasingly relies on vision-language models (VLMs) to translate instructions and…