dLLMs
PulseAugur coverage of dLLMs — every cluster mentioning dLLMs across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
FINDERS framework uses diffusion models for adaptive user representation
Researchers have introduced FINDERS, a novel framework that leverages diffusion language models (dLLMs) to create more adaptive user representations. Unlike existing methods that compress user behavior into static forma…
-
New LEAP method boosts Diffusion Language Model parallelism by 30%
Researchers have developed LEAP, a novel method to enhance the parallelism of Diffusion Language Models (dLLMs). LEAP addresses the limitations of current dLLMs, which require high confidence levels for parallel process…
-
Diff Diffusion framework offers faster, more efficient AI code editing
Researchers have developed Diff Diffusion, a new framework for AI-assisted code editing that utilizes diffusion models to predict edit paths. Unlike models optimized for sequence synthesis, Diff Diffusion focuses on spa…
-
New Denoising Workload Surface improves dLLM inference cost prediction
Researchers have introduced the Denoising Workload Surface (DWS) to more accurately model and predict the inference costs of diffusion large language models (dLLMs) during serving. Traditional cost proxies are insuffici…
-
New methods accelerate diffusion language model inference · 4 sources tracked
Researchers are developing new methods to accelerate inference for diffusion language models (DLMs), which are computationally intensive due to their iterative denoising process. One approach, Window-Diffusion, uses a s…
-
New methods accelerate LLM inference speed via speculative decoding
Two new research papers introduce novel methods for accelerating the inference speed of large language models. The first paper, "ReTrace," proposes a technique that conditions each draft block on the rejected suffix fro…
-
New CForce method boosts parallel decoding for diffusion LLMs
Researchers have introduced Consistency Forcing (CForce), a new distillation method designed to improve the parallel decoding capabilities of diffusion large language models (dLLMs). This technique addresses the issue o…
-
Ripple-Pivot Search accelerates Diffusion LLM inference by up to 18x
Researchers have introduced Ripple-Pivot Search (RPS), a new decoding method for Diffusion Large Language Models (dLLMs) that significantly speeds up inference. RPS exploits a "ripple effect" where committing to a mid-e…
-
DC-Leap framework accelerates dLLMs with training-free decoding
Researchers have introduced DC-Leap, a novel training-free framework designed to accelerate the inference speed of Diffusion Large Language Models (dLLMs). This method addresses the issue of conservative confidence thre…
-
New research accelerates diffusion language model training and enhances generation
Researchers are exploring advancements in Masked Diffusion Language Models (MDMs) to improve their training efficiency and generative capabilities. One study proposes a 'bell-shaped time sampling' strategy that accelera…
-
New LLM Frameworks and Benchmarks Advance Formal Mathematical Reasoning
Researchers are developing new methods and benchmarks to improve the formal mathematical reasoning capabilities of large language models (LLMs). One approach, Diffusion-Proof, utilizes diffusion LLMs (dLLMs) for theorem…