GitHub 新星
10 条
arXiv 论文
10 条
-
1
CSF: Contextual Safety Filtering for Motion Generators
Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person. Existing safeguards eitherLizhi Yang, Yiling Hou, Yao Tang
-
2
On the estimation and validity of AI time horizons---a statistical look at the METR plot
METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks andDrew T. Nguyen, William Fithian
-
3
A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control
General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful tool for this goal, cOcti Zhang, Mateo Guaman Castro, Patrick Yin
-
4
From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research iAbbas Raftari
-
5
BrickBench: Evaluating Agentic Brick Design
We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and design criteria, butPeter Kulits, Yiqing Xu, R. Kenny Jones
-
6
One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillatioAdrian Bulat, Yassine Ouali, Georgios Tzimiropoulos
-
7
Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems
Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetry-breaking bifurcation, a singAnna Zimmel, Fleur Hendriks, Markus Holzleitner
-
8
Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception
Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier mOskar J. Hollinsworth, Alex F. Spies, Tigist Diriba
-
9
Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization
Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent adaptive updates. We redesign 4-bit optimizer-stHanyang Li, Shao Tang, Daniel Thomas Braithwaite
-
10
Density Ratio Estimation with Stein Displacement Fields
Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is transported onto anotherSong Liu
Hacker News
10 条
- 1 IRCv3
- 2 Total Annihilation, rebuilt for modern computers
- 3 NYC's "Click to Cancel" rule is now in effect
- 4 Terence Tao: Math 2.0 [pdf]
- 5 So, You’d Like To Sell Your Print Issues Of The Onion?
- 6 The gap in shared understanding of LLM capability is widening
- 7 Passkeys are a trap. Do not use them
- 8 The tilde in your PATH may not be your HOME
- 9 Cartographers of North Korea (2019)
- 10 500B tokens later: Letting AI agents decompile a first-person shooter