norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers1 hour ago
ResearchDaily Papers

MEND: RL for Flow Models via Proximal Velocity Matching

MEND is a reinforcement learning method for flow models that uses proximal velocity matching to cap rewards within each prompt group, proposing moves along the reward gradient only when the reward gain exceeds a quadratic displacement cost. It outperforms existing methods like Flow-GRPO, ReFL, and DiffusionNFT with fewer updates and without requiring a KL term or frozen reference model.

Open original
SIGNAL FROM THE SOURCE
1
source votes
Tracking sinceOctober 7, 20261 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedOctober 5, 2026Shreshth Saini, Neil Birkbeck, Yilin Wang
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

1 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

MEND offers a more efficient and effective approach to reward post-training of flow models by capping rewards and using gradient-based moves with a displacement cost, achieving better performance with fewer updates.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

RealCompanion introduces a benchmark for evaluating AI's ability to understand humans through long-term conversations, featuring 27,218 messages from 10 real relationships. The study reveals that most queries don't require long-term memory and that current methods struggle to identify when memory is needed.

6 days agoDaily Papers

Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation

Ego2Act is a benchmark for evaluating goal-directed manipulation in egocentric video generation, featuring 2,640 videos from 110 real-world tasks. It assesses whether video generation models can create realistic egocentric videos of a hand performing multi-step object manipulations to achieve high-level goals.

6 days agoDaily Papers

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

The paper investigates on-policy distillation (OPD) in cross-tokenizer settings, focusing on alignment coverage and supervision reliability. It finds that strict 1:1 token alignment covers most student-generated tokens despite vocabulary mismatches, and that restricting reverse KL to a top-16 subset of shared vocabulary achieves comparable accuracy to full shared-vocabulary OPD, while adding span supervision reduces accuracy.

yesterdayDaily Papers

World Action Learning via Interaction-Centric Spectral Latent Guidance

The paper introduces WING, a framework that transfers interaction knowledge from human egocentric videos to robot policies by separating observer-induced motion from hand-object interactions and using spectral analysis to identify shared temporal structures between human and robot behaviors. It achieves high success rates on multiple benchmarks and demonstrates strong performance in real-world tasks.

5 days agoDaily Papers

World Action Modeling with Progressive Visual Planning

This paper introduces ProWAM, a progressive world action model that predicts actions and sparse visual sub-goals to guide robotic control. It improves long-horizon planning by using a single video-backbone pass for efficient action generation and demonstrates strong performance on simulation and real-world benchmarks.

6 days agoLessWrong

Determining the Date Without Real-Time Data

The text discusses a scenario where an AI must respond to the question 'What's the date?' without access to real-time data. It explores the challenge of providing an accurate date without hallucinating, considering OpenAI's training focus on avoiding false information. The text speculates on potential model versions and knowledge cutoff dates but acknowledges uncertainty due to lack of explicit information.

6 days ago