Entities · Models
LLaMA
58 articles tagged with this entity.
-
The Key to Going Linear: Analysis-Driven Transformer Linearization
-
This startup thinks robotics is about to have its ChatGPT moment
-
Effective Distillation to Hybrid xLSTM Architectures
-
Deriving Neural Scaling Laws from the statistics of natural language
-
ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
-
Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
-
Has This Checkpoint Been Abliterated? A Two-Signal Audit and Its Failure Map
-
Compressed Sensing for Capability Localization in Large Language Models
-
Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats
-
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
-
RAS: Measuring LLM Safety Through Refusal Alignment
-
Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs
-
AI Supply Chain Galaxy: 3D Visual Analytics for License Compliance
-
TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation
-
Localizing Anchoring Pathways in Language Models
-
Optimal Post-Training Quantization Scales and Where to Find Them
-
Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions
-
LLM-Based Code Documentation Generation and Multi-Judge Evaluation
-
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
-
LoRi: Low-Rank Distillation for Implicit Reasoning
-
WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization
-
Model Parallelism With Subnetwork Data Parallelism
-
Child-directed speech facilitates production, not comprehension, in BabyLMs
-
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
-
SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding
-
HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
-
Re-examining Low Rank adaptation for private LLM fine-tuning
-
Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data
-
Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization
-
Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging
-
Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules
-
Comparative Evaluation of Machine Translation Systems on Images with Text
-
FoRA: Fisher-orthogonal Rank Adaptation for Parameter-Efficient Fine-Tuning
-
Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders
-
AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
-
Faithfulness Evaluation for Decoder-only LLM Attributions with Controlled Retained Information
-
The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
-
Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
-
Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study
-
AI Content Moderation in Therapy Conversations
-
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
-
Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
-
SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
-
Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
-
Krause Synchronization Transformers
-
Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
-
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
-
The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models
-
SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models
-
Learning When to Adapt
-
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
-
Test-Time Compute Games
-
Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization
-
Annotation Quality in Aspect-Based Sentiment Analysis: A Case Study Comparing Experts, Students, Crowdworkers, and Large Language Model
-
Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models
-
CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
-
Activation Compression in LLMs: Theoretical Analysis and Efficient Algorithm
-
AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs