norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers2 hours ago
ResearchDaily Papers

MemBodied: Recurrent Associative Memory for Vision-Language-Action Models

MemBodied introduces a fixed-size episodic memory for vision-language-action models, combining an associative state and an episode anchor to improve performance in history-dependent tasks. It achieves significant success rate improvements over stateless policies and recurrent memory baselines with fewer parameters.

Open original
SIGNAL FROM THE SOURCE
8
source votes
Tracking sinceSeptember 24, 20268 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 23, 2026Tej Deep Pala, Navonil Majumder, Bryce Goh
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.

8 source votes

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

WHY IT MAY MATTER

MemBodied provides an efficient way to handle history-dependent tasks in robot control without expanding the policy context, making it suitable for real-world applications with limited computational resources.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts

IntBMoE introduces a block-conditioned Mixture-of-Experts (MoE) framework that decouples participation, execution, and materialization by combining dense expert composition with sparse block execution. It uses a learned codebook for blocks and a hypernetwork to merge experts, achieving full participation while keeping execution and memory costs low. Experiments show improvements in image classification, language modeling, and sequential recommendation, with real-world deployment in AMap's recommendation system.

6 days agoDaily Papers

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

The paper introduces Taste-Bench, a benchmark for evaluating an agent's 'taste' in making long-horizon decisions. It measures the ability to choose the better path in decision forks without knowing future outcomes, revealing that current models perform poorly and that taste can be improved through distillation.

2 days agoDaily Papers

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

The paper introduces Document Retrieval-Aware Chunking (D-RAC), a method for efficiently processing enterprise documents by normalizing them into PDF and converting them into retrieval-optimized Markdown using a multimodal LLM. This approach preserves document structure, reduces token costs, and improves chunking efficiency compared to traditional methods.

3 days agoDaily Papers

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

This paper introduces an all-in-one multilingual scene text recognition system that uses a script-aware Mixture-of-Experts (MoE) architecture. The system, called ScriptMoE, outperforms existing methods on multilingual text recognition tasks by leveraging a large synthetic dataset and a lightweight architecture that shares a visual encoder while using script-specific experts for decoding.

3 days agoDaily Papers

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

CodeMidas is an agentic pipeline that converts implemented functionality in open-source codebases into executable reinforcement learning (RL) environments using only source code as input. It generates 5,545 training tasks from 3,185 codebases across 23 languages and 15 domains, improving performance on multiple coding benchmarks when training MiMo-V2.5 with GRPO.

6 days agoLessWrong

What if Not Circuits?

The post explores the author's confusion about how neural networks, particularly large language models (LLMs), perform and learn computations. It challenges the conventional 'mechinterp' (mechanistic interpretation) approach that relies on circuit-based explanations, arguing that 'circuits' and 'computation' may not be the most suitable framework for understanding LLMs. The essay discusses representational drift as a key obstacle to weight-based circuit analysis and suggests a 'co-selectionist' view of circuits as emergent units. The author also reflects on how the concept of 'universality' should influence explanations of LLM function.

2 days ago