Category
2,926 papers
A dynamic per-layer scalar derived by adapting the LARS/LAMB trust-ratio principle to the orthogonalized setting, where the standard denominator candidates---the raw momentum norm or the polar-factor norm---either live in the wrong unit space or carry no update-scale information.
These results expose a rate-granularity trade-off: PairAlign does not uniformly outperform denser tokenizers on every local metric, but provides a lower-rate symbolic interface preserving ordered and relational structure.
Personalized GRPO is introduced, a novel alignment framework that decouples advantage estimation from immediate batch statistics and achieves faster convergence and higher rewards than standard GRPO, thereby enhancing its ability to recover and align with heterogeneous preference signals.
MUSE (Multimodal Unified Safety Evaluation), an open-source, browser-based, run-centric platform for multimodal safety evaluation, demonstrates the value of run-centric, fine-grained evaluation for characterizing multimodal safety behavior beyond a single binary success metric.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces Constrained GRPO, a Lagrangian-based extension of GRPO for constrained policy optimization, and addresses the coupling induced by reward scalarization by scalarizing standardized advantages rather than rewards.
It is suggested that diffusion post-training selectively preserves or reorganizes inherited computation according to task structure, rather than uniformly replacing autoregressive mechanisms.
BAFA, the Bounded Active Fairness Auditor is introduced, the Bounded Active Fairness Auditor for query-efficient auditing of black-box LLMs, suggesting that active sampling can reduce resources needed for independent fairness auditing with LLMs, supporting continuous model evaluations.
ScalePRM, which scales verification compute as an alternative to ground-truth supervision for training process reward models, generates multiple independent verifications of each reasoning step and aggregate their judgments to produce synthetic step-level labels without ground truth.
KronSAE is proposed, a design that factorizes the latent space into heads and forms post-latent features as pairwise compositions of lower-dimensional pre-latents using mAND, a differentiable AND-like interaction that imposes a compositional co-activation prior while remaining compatible with standard SAE objectives and variants.
Layer-Integrated Memory (LIMe) is introduced, a lightweight extension that leverages existing key-value buffers and learns per-head, per-layer routing weights to integrate representations from previous layers to improve perplexity per FLOP and yield strong gains on synthetic tasks while preserving higher value-vector entropy and token separability.
This work interprets chain-of-thought reasoning as a latent variable modeling problem and demonstrates that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training and reward-maximizing policy optimization.
AutoSciRub is presented, an evaluation-first framework that induces a task-specific executable rubric before research execution and uses it to guide execution, criterion-level verification as well as iterative revision.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
Algorithms & Theory
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
