manipulation
Borda count and manipulable rankings: why no vote-based leaderboard is gaming-proof Lesson
Every rule that turns many people's preferences into one ranking can be manipulated in some situations, which is why open arena-style AI leaderboards need defenses and why a single rank should be treated as one signal.
'Leaderboard Hacking' paper: votes, prompts and decoy models can lift an arena ranking by up to 45 places News
A November 10 preprint by Fleisig, Baumann, Hadfield-Menell and Hovy shows that arena-style leaderboards built on the Bradley-Terry model can be manipulated, with each attack moving a model 15 to 20 places and all three combined up to 45.
Robot Policies That Predict the Touch Before They Make It News
Two matched robotics releases from NeoteAI and Fudan give manipulation policies a sense of touch that anticipates contact rather than reporting it, winning all nine real-robot tasks in the authors' benchmark against strong vision-only baselines.
A handheld gripper and a head camera can now train robots with no robot demonstrations News
Researchers report that raising the fidelity of handheld human demonstrations removes the need for any robot teleoperation on the target task, with policies trained on handheld data alone reaching parity with robot-taught baselines on four two-armed tasks.
A robot hand learns to open things by reasoning about touch, not video News
New research teaches multi-finger robot hands to manipulate things with moving parts — handles, drawers, hinges — by focusing on contact points, and stays steady even without touch sensors.
HiFi-UMI-2K Tool
Released dataset behind this week's handheld-only robot training result: high-fidelity two-handed human demonstrations captured with a head-mounted stereo rig and tracked grippers, with every trajectory reconstructed and rejected unless a target robot could physically replay it. Covers wiping, shirt folding, remote insertion and produce sorting. Directly usable for imitation-learning experiments without owning a teleoperation setup.