Awesome-LLMs-ICLR-24
Enrichment pendingIt is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.
GraphCanon updated today · GitHub synced today
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (831d since push)
- As of today
- Provenance
- Not a fork · Personal account
- As of today
- Security (OSV)
- No lockfile
- As of today
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/azminewasi/Awesome-LLMs-ICLR-24Similar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.
Capability facts
No sourced capability facts yet. Facts appear after ingest scans repo manifests (Dockerfile, package.json, MCP configs).
Categories
Tags
README
Grounding Language Plans in Demonstrations Through Counter-Factual Perturbations
This paper explores the potential of Large Language Models (LLMs) to improve robot manipulation by leveraging concepts from plan-ning literature. Specifically, the authors introduce a framework that uses LLMs to ground abstract language representations into low-level physical trajectories, enabling the learning of structured policies for manipulation tasks.
Details
- Abstract: Grounding the abstract knowledge captured by Large Language Models (LLMs) in physical domains remains a pivotal yet unsolved problem. Whereas prior works have largely focused on leveraging LLMs for generating abstract plans in symbolic spaces, this work uses LLMs to guide the learning for structures and constraints in robot manipulation tasks. Specifically, we borrow from manipulation plan- ning literature the concept of mode families, defining specific types of motion constraints among sets of objects, to serve as an intermediate layer that connects high-level language representations with low-level physical trajectories. By lo- cally perturbing a small set of successful human demonstrations, we augment the dataset with additional successful executions as well as counterfactuals that fail the task. Our explanation-based learning framework trains neural network-based classifiers to differentiate success task executions from failures and as a by-product learns classifiers that ground low-level states into mode families without dense labeling. This further enables us to learn structured policies for the target task. Experimental validation in both 2D continuous-space and robotic manipulation environments demonstrates the robustness of our mode-based imitation methods under external perturbations.
- OpenReview: https://openreview.net/pdf?id=qoHeuRAcSl
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
Model down-scaling techniques differentially impact large language models' capabilities, with weight pruning significantly impairing factual recall but preserving context processing, while model shrinkage affects recall more than context processing.
Details
- Abstract: We study how down-scaling large language model (LLM) size impacts LLM capabilities. We begin by measuring the effects of weight pruning a popular technique for reducing model size on the two abilities of LLMs: (a) recalling facts presented during pre-training and (b) processing information presented in context. Surprisingly, we find that existing pruning techniques affect these two abilities of LLMs differently. For example, pruning more than 30% of weights significantly decreases an LLMs ability to recall facts presented during pre-training. Yet pruning 60-70% of weights largely preserves an LLMs ability to process information in-context, ranging from retrieving answers based on information presented in context to learning parameterized functions such as a linear classifier based on a few examples. Moderate pruning impairs LLMs ability to recall facts learnt from pre-training. However, its effect on models ability to process information presented in context is much less pronounced. The said disparate effects similarly arise when replacing the original model with a smaller dense one with reduced width and depth. This similarity suggests that model size reduction in general underpins the said disparity.
- OpenReview: https://openreview.net/pdf?id=ldJXXxPE0L
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
This research combines language learning models with reinforcement learning to guide robots in complex tasks, without requiring predefined skills. The proposed approach, Plan-Seq-Learn, uses motion planning to translate abstract language instructions into low-level control action
For agents
This page has a .md twin and JSON over the API.