All news
10623
New Survey Maps AI in Humanitarian Work: Six Tasks, From Weather to Refugees
A survey on Hugging Face Daily Papers describes AI as a tool for six humanitarian tasks: weather forecasting, energy, forests, poverty, post-disaster damage and…
ARC-SORT hits 81.82 HOTA on SportsMOT and runs at 50 fps
The training-free ARC-SORT tracker scores 81.82 HOTA on SportsMOT with the fewest ID switches among 69 entries, and runs at about 50 fps on a laptop RTX 3060.
SciΠvot benchmark: the best LLM picks the right plan 63.5% of the time, versus 73.4% for humans
A benchmark of 248 senior-researcher corrections finds the best model picks the right call 63.5% of the time; fresh researchers hit 73.4%. Project context tends to…
Cohere pitches utilities on running North AI agents inside their own perimeter
LLM-Attacker Benchmarks Split-LLM Attacks: Gradients Raise Leakage to 37.77%
Data Rewriting Beats DP-SGD on the Privacy-Quality Trade-Off
Kolab: 115 Hours of Recordings Show That AI Agents Don't Understand Their Human Colleagues
DialFork measured procedural hallucinations in agents across 36,278 dialogues
The DialFork benchmark catches agents that sound smooth and factually correct but drift off script. It includes 36,278 dialogues, 24 tasks, 12 domains, and two new…
AlphaBet trains an LLM agent to forecast events: Brier score improves 14.4%
Researchers trained GLM-4.5-Air to search for data and give probabilities across several dates. Brier on Forecast-Dojo fell from 0.731 to 0.626, on FutureX from…
OpenAI Engineer Hid a "Bug" in Toilet Paper and Got Caught Within 48 Hours
OpenAI shows how ChatGPT builds a catering pitch for a Toronto restaurant
Natura-1 Teaches Robots Dexterous Hands With a Million Hours of Human Experience
Apple's LensVLM compresses long agent context into images and teaches the model to "zoom"
Tsinghua Unveils Jev-LDE: Edit ICL Examples Once, Boost 1-Shot Accuracy
Tsinghua researchers propose Jev-LDE, a method that edits in-context learning examples once and noticeably raises average 1-shot accuracy.
Recursia Beats Nvidia ASPIRE by 10 Points on Long-Horizon Robot Tasks
Recursia, built on the Embodied RSI paradigm, targets zero-shot generalization in robots. On long multi-step tasks, it outperforms Nvidia ASPIRE by 10 points.