LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
hub
Language models are unsupervised multitask learners
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
GAE reduces the faithfulness gap in dictionary-based explainers under distribution shift by geometrically realigning the ID dictionary to the OOD-active subspace, with a quadratic excess-loss bound.
RepoBench is a new benchmark with retrieval, completion, and pipeline tasks to evaluate code auto-completion systems on entire repositories instead of single files.
In a stylized one-layer transformer, pre-training encodes factual knowledge via relation-specific feature directions and attention patterns; fine-tuning extracts it through a relation-covering mechanism that succeeds when enough latent templates are triggered, with a failure regime explaining inauds
LLMs show partial and variable perceptual alignment with human touch on textiles, succeeding on samples like silk satin but failing on cotton denim when matching descriptive language to embedding similarity.
Gradual fine-tuning that removes explicit CoT steps lets GPT-2 Small reach 99% accuracy on 9x9 multiplication and Mistral 7B exceed 50% on GSM8K with no intermediate outputs.
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
HoloMotion-1 trains a MoE Transformer policy on hybrid video and MoCap motion data to achieve robust zero-shot tracking that transfers directly to real humanoid robots.
Causal Path Alignment anchors optimization trajectories in in-parameter knowledge editing to follow relation-aware causal paths, reducing subject-dominant memory interference in LLMs.
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
citing papers explorer
-
LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
LIBERO is a new benchmark for lifelong robot learning that evaluates transfer of declarative, procedural, and mixed knowledge across 130 manipulation tasks with provided demonstration data.
-
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
GAE reduces the faithfulness gap in dictionary-based explainers under distribution shift by geometrically realigning the ID dictionary to the OOD-active subspace, with a quadratic excess-loss bound.
-
RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
RepoBench is a new benchmark with retrieval, completion, and pipeline tasks to evaluate code auto-completion systems on entire repositories instead of single files.
-
Provable Knowledge Acquisition and Extraction in One-Layer Transformers
In a stylized one-layer transformer, pre-training encodes factual knowledge via relation-specific feature directions and attention patterns; fine-tuning extracts it through a relation-covering mechanism that succeeds when enough latent templates are triggered, with a failure regime explaining inauds
-
TouchAI: Exploring human-AI perceptual alignment in touch through language model representations
LLMs show partial and variable perceptual alignment with human touch on textiles, succeeding on samples like silk satin but failing on cotton denim when matching descriptive language to embedding similarity.
-
From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
Gradual fine-tuning that removes explicit CoT steps lets GPT-2 Small reach 99% accuracy on 9x9 multiplication and Mistral 7B exceed 50% on GSM8K with no intermediate outputs.
-
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
-
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
CAMEL proposes a role-playing framework with inception prompting that enables autonomous multi-agent cooperation among LLMs and generates conversational data for studying their behaviors.
-
HoloMotion-1 Technical Report
HoloMotion-1 trains a MoE Transformer policy on hybrid video and MoCap motion data to achieve robust zero-shot tracking that transfers directly to real humanoid robots.
-
Causal Path Alignment: Anchoring the Optimization Trajectory for Controllable In-Parameter Knowledge Editing
Causal Path Alignment anchors optimization trajectories in in-parameter knowledge editing to follow relation-aware causal paths, reducing subject-dominant memory interference in LLMs.
-
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
MiniGPT-v2 adds unique task identifiers to a large language model so one system can perform image description, visual question answering, and visual grounding after three-stage training.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.