conftrace_

token prediction

49 papers

Explore in graph

Co-occurring keywords

large language model (13587) language model (4599) speculative decoding (111) autoregressive model (456) image generation (2073) inference acceleration (244) autoregressive decoding (33) code generation (746) uncertainty quantification (1393) causal intervention (110)

Papers

Enabling Autoregressive Models to Fill In Masked Tokens EACL 2026
Multi-Aspect Cross-modal Quantization for Generative Recommendation AAAI 2026
Constrained Sequential Inference in Machine Learning Using Constraint Programming IJCAI 2025
Overlapping Context with Variable-Length Stride Increases Diversity when Training Large Language Model for Code ACL 2025
Finetuning LLMs for EvaCun 2025 token prediction shared task NAACL 2025
EvaCun 2025 Shared Task: Lemmatization and Token Prediction in Akkadian and Sumerian using LLMs NAACL 2025
TAPNext: Tracking Any Point (TAP) as Next Token Prediction ICCV 2025
Accelerated Test-Time Scaling with Model-Free Speculative Sampling EMNLP 2025
EditAR: Unified Conditional Generation with Autoregressive Models CVPR 2025
Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction CVPR 2025
Certain but not Probable? Differentiating Certainty from Probability in LLM Token Outputs for Probabilistic Scenarios EMNLP 2025
Adaptive Draft-Verification for Efficient Large Language Model Decoding AAAI 2025
Unified Video Generation via Next-Set Prediction in Continuous Domain ICCV 2025
Training-Free Text-Guided Image Editing with Visual Autoregressive Model ICCV 2025
TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation ICCV 2025
Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal Cycles ACL 2025
Denoising Token Prediction in Masked Autoregressive Models ICCV 2025
Grouped Speculative Decoding for Autoregressive Image Generation ICCV 2025
DReSD: Dense Retrieval for Speculative Decoding ACL 2025
Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts ACL 2025
Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs EMNLP 2025
Evil twins are not that evil: Qualitative insights into machine-generated prompts EMNLP 2025
Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models EMNLP 2025
Knowledge Editing Induces Underconfidence in Language Models EMNLP 2025
Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models EMNLP 2024