Category
19,710 papers
Results show that successful task completion can coexist with unauthorized post-hoc disclosure and motivate host-controlled authorization for secondary tool calls and motivate host-controlled authorization for secondary tool calls.
Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning. On-policy distillation narrows such gaps by supervising a student on its own rollouts, but traditional OPD requires a st...
This work introduces Rollback, a policy improvement paradigm that turns world models from passive simulators into counterfactual engines, and builds a scalable training system that unifies distributed world-model search with asynchronous real-robot execution, forming a self-reinforcing cycle.
On short, precisely specified programs, current coding agents localize nearly all faults from source code alone, and debugger assistance removes most errors that remain.
Reach audiences
Advertise in front of researchers, engineers, and readers.
CIVER is proposed, a causal intervention-based framework that identifies the core issues underlying code-review findings and distinguishes genuine defects from false positives and generalizes across repositories and improves coding agents' success rates, highlighting its effectiveness for reliable automated code review...
Sparse expert execution does not remove the stored states needed to adapt a mixture-of-experts language model. We present DuplexTune, a framework for replaying coupled hidden states through pretrained attention and expert modules. Trainable width bridges connect two residual streams to the backbone. Bridge warm-up prec...
These findings establish open System One models as a promising zero shot baseline for medical AI, combining competitive predictive performance with low computational cost and efficient local calibration, and introduce a lightweight, two parameter recalibration method.
PolicyMediator is introduced, a cognition-constrained leader-multi-follower Stackelberg framework with bilateral mediation that improves the aggregate government objective, combining economic performance, employment benefit, and policy-access equality, by 42.4% and average OPC utility by 40.9%.
This work exploits transactions already recorded by both endpoint banks to approximate remote account states locally, enabling multi-layer Graph Neural Network computation without additional account-specific exchange and support a practical rule for banks: use what they already record, and formally protect the little t...
Variable-length training creates conflicting parallelism requirements across the layers of a hybrid-attention model. The longest samples require wide sequence-parallel (SP) groups of 16 or 32 ranks for full attention, whose cost grows quadratically with sequence length. Sparse-attention layers, dominated by near-linear...
Proactive bug discovery is an important software-engineering problem. Even though coding agents are already widely deployed in this domain, their capabilities remain understudied. In particular, the challenging task of finding all bugs that human maintainers would repair across an entire repository has not been studied...
Conditional memory layers, such as DeepSeek's Engram, attach large hashed n-gram tables to a language model, and removing them from DeepSeek-V4.1-Flash costs 36.8 PopQA points. Low-bit quantization loses long-tail facts first, and the standard remedy, giving more bits to frequently accessed rows, backfires: refining lo...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
