REVIEW 12 cited by
Depth-Adaptive Transformer
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Depth-Adaptive Transformer
read the original abstract
State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process. In this paper, we train Transformer models which can make output predictions at different stages of the network and we investigate different ways to predict how much computation is required for a particular sequence. Unlike dynamic computation in Universal Transformers, which applies the same set of layers iteratively, we apply different layers at every step to adjust both the amount of computation as well as the model capacity. On IWSLT German-English translation our approach matches the accuracy of a well tuned baseline Transformer while using less than a quarter of the decoder layers.
Forward citations
Cited by 12 Pith papers
-
Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference
A sleep mechanism with N offline recurrent passes consolidates context into fast weights, improving performance on reasoning tasks where standard transformers fail.
-
Fast Inference from Transformers via Speculative Decoding
Speculative decoding accelerates exact sampling from large autoregressive models by 2-3x on T5-XXL by running smaller approximation models in parallel to propose token sequences that the large model then verifies in b...
-
Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts
In looped transformers, halting-gate failures come mainly from how gate training reshapes the trajectory; fixed-prior depth supervision plus simple confidence readouts yields better accuracy per unit of compute.
-
Generative Recursive Reasoning
GRAM turns recursive latent reasoning into a generative probabilistic model via stochastic trajectories and amortized variational inference, claiming better performance on structured reasoning tasks than deterministic...
-
Generative Recursive Reasoning
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
-
Compute Where it Counts: Self Optimizing Language Models
SOL trains a policy to dynamically control multiple efficiency mechanisms per token via group-relative policy optimization on teacher-forced episodes, yielding better quality at matched average budget than static or r...
-
LPC-SM: Local Predictive Coding and Sparse Memory for Long-Context Language Modeling
LPC-SM is a hybrid architecture separating local attention, persistent memory, predictive correction, and control with ONT for memory writes, showing loss reductions on 158M-parameter models up to 4096-token contexts.
-
Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
An early-exit rule with a zero-shot fallback, calibrated by Learn-then-Test risk control, keeps the average loss from corrupted in-context demonstrations under a preset bound.
-
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Mixture-of-Depths enables transformers to dynamically allocate compute by routing only the top-k tokens through each layer's full computations, matching baseline performance with a fraction of the FLOPs per forward pa...
-
GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding
GShard supplies automatic sharding and conditional computation support that enabled training a 600-billion-parameter multilingual translation model on thousands of TPUs with superior quality.
-
ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents
ToolGate is a pre-call controller that reduces token usage in tool-augmented VLM agents to 64-69% of baseline while preserving or slightly improving accuracy on benchmarks.
-
ITS-Mina: A Harris Hawks Optimization-Based All-MLP Framework with Iterative Refinement and External Attention for Multivariate Time Series Forecasting
ITS-Mina introduces an all-MLP model with iterative refinement, external attention via learnable memory units, and HHO-tuned dropout that reports state-of-the-art or competitive results on six multivariate time series...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.