DataComp-VLM benchmark shows instruction-heavy data mixing outperforms filtering for VLM training, with DCVLM-Baseline achieving 63.6% on 33 tasks for 8B models (+5.4pp over FineVision).
super hub Mixed citations
GLU Variants Improve Transformer
Mixed citation behavior. Most common role is background (47%).
269
Pith papers citing it
Background
47% of classified citations
abstract
Gated Linear Units (arXiv:1612.08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Variations on GLU are possible, using different nonlinear (or even linear) functions in place of sigmoid. We test these variants in the feed-forward sublayers of the Transformer (arXiv:1706.03762) sequence-to-sequence model, and find that some of them yield quality improvements over the typically-used ReLU or GELU activations.
hub tools
citation-role summary
background 30
method 24
dataset 2
extension 1
citation-polarity summary
claims ledger
- abstract Gated Linear Units (arXiv:1612.08083) consist of the component-wise product of two linear projections, one of which is first passed through a sigmoid function. Variations on GLU are possible, using different nonlinear (or even linear) functions in place of sigmoid. We test these variants in the feed-forward sublayers of the Transformer (arXiv:1706.03762) sequence-to-sequence model, and find that some of them yield quality improvements over the typically-used ReLU or GELU activations.
authors
co-cited works
representative citing papers
Depth-L transformers with W parameters have VC dimension Theta(L W log(T W)), yielding matching O(L W log((T+T')W)) upper and Omega(L W log((T+T')W/L)) lower bounds on sample complexity for chain-of-thought learning.
CLAD is the first deep learning framework for log anomaly detection that operates directly on compressed byte streams using a dilated convolutional encoder, hybrid Transformer-mLSTM, and two-stage training, achieving 0.9909 average F1-score across five datasets.
Test-time training with KV binding reduces to learned linear attention.
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.
A transformer-based diffusion model learns the joint distribution of convergence maps and cosmology from log-normal weak lensing simulations and generates calibrated posterior samples matching MCMC results.
DTM-Codec achieves better reconstruction quality and intelligibility than fixed-frame-rate neural speech codecs at matched total bitrate via dynamic token masking and Path Length Equalization for variable frame rates.
PRA approximates sequential rollout training in parallel for pixel-space AR models via intermediate states and a pixel decoder, achieving FID 2.58 (135M params) and 1.94 (511M params) on ImageNet-1K 256x256, new SOTA among pixel-space AR models.
MADField is a multi-fidelity amortized model for predicting density fields to improve accuracy and speed of adsorption calculations in nanoporous materials for high-throughput screening.
AttentionCap, a customized Transformer, predicts capacitance matrices across multiple process nodes with 0.67% self-capacitance and 3.99% coupling error on unseen designs, outperforming CNN baselines in accuracy and speed.
Stateful visual encoders condition each visual representation on prior features, yielding consistent gains on multi-image tasks under supervised finetuning across model sizes and domains.
A large-scale empirical study across tokenizers and diffusion backbones identifies Velocity Irreducible Variance (VIV) as one of the most stable predictors of latent diffusion generation quality.
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
mRNAutilus generates full-length therapeutic mRNAs via diffusion models and multi-objective guidance, achieving over 400-fold expression gains for luciferase and outperforming baselines for Spike and other targets in zero-shot tests.
Introduces Chess-World-Model benchmark from 10M chess games showing recurrent models (SLiCE, Mamba-3, Gated DeltaNet) outperform Transformers on exact state tracking, with random-play split remaining hard at larger scales.
An in-vitro study with synthetic languages finds cross-lingual transfer depends more on tokenization preserving reusable substructure than on lexical similarity or balance, with transfer emerging in stages.
Bilingual fine-tuning on a new parallel Filipino-English dementia dataset yields Macro-F1 scores of 0.969-0.973 and eliminates cross-lingual degradation for all tested transformers.
MuCRASP prunes VLMs in a CoT-aware manner, outperforming baselines by preserving reasoning quality at 30-50% compression rates on models like Qwen2.5-VL-7B.
DiSI disentangles stochastic interpolants into separate generation and regression paths, allowing controllable transitions between regression and generative image restoration with a unified few-step sampler.
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
φ-balancing is a convex optimization method for population-level expert balance in MoE training that derives an online EMA adjustment and outperforms heuristic baselines.
VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
PSR-NQS makes recurrent neural quantum states scalable for variational Monte Carlo by using parallel scan recurrence, reaching accurate results on 52x52 two-dimensional lattices.
citing papers explorer
-
Large Language Diffusion Models
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
-
Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
Width pruning in Llama-3.2 models reduces parametric knowledge while enhancing instruction-following and preserving reasoning.
-
Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs
Cascaded systems remain the most reliable for speech translation overall, but recent SpeechLLMs match or outperform them in many conditions while standalone speech models lag.
-
Less is More: Recursive Reasoning with Tiny Networks
TRM with 7M parameters achieves 45% accuracy on ARC-AGI-1 and 8% on ARC-AGI-2, surpassing most LLMs with under 0.01% of their parameters.
-
Training Agents Inside of Scalable World Models
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.
-
ViT$^3$: Unlocking Test-Time Training in Vision
ViT³ is a Test-Time Training vision model that achieves linear complexity, matches or exceeds other linear models like Mamba on classification, generation, detection and segmentation, and narrows the gap to standard vision Transformers.
-
Back to Basics: Let Denoising Generative Models Denoise
Directly predicting clean data with large-patch pixel Transformers enables strong generative performance in diffusion models where noise prediction fails at high dimensions.
-
Emu3.5: Native Multimodal Models are World Learners
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
-
Vision-LLMs for Spatiotemporal Traffic Forecasting
ST-Vision-LLM reframes spatiotemporal traffic forecasting as vision-language fusion, using visual encoders on traffic grids and efficient numerical tokenization to achieve 15.6% better long-term accuracy and 30% gains in few-shot cross-domain settings.
-
From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill
Layered prefill replaces token-chunked prefill with layer-group interleaving in MoE models, cutting TTFT by up to 70%, end-to-end latency by 41%, and per-token energy by 22% while preserving stall-free TBT.
-
Scaling Sequence-to-Sequence Generative Neural Rendering
Kaleido is a masked autoregressive generative model that unifies 3D view synthesis and video modeling by pre-training a single transformer on video data, achieving SOTA zero-shot and many-view performance on view synthesis benchmarks.
-
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
-
Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining
Sparse crosscoders on LLM checkpoint triplets track emergence, maintenance, and discontinuation of linguistic features during pretraining via a new RelIE metric.
-
mGRADE: Minimal Recurrent Gating Meets Delay Convolutions for Lightweight Sequence Modeling
mGRADE uses learnable-spaced convolutions shown to be equivalent to delay embeddings plus a lightweight gated recurrent component to achieve low-memory multi-timescale sequence modeling.
-
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Math reasoning gains in LLMs rarely transfer to general domains; RL tuning generalizes while SFT causes forgetting and representation drift.
-
Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource
MoE models with activation rates in an optimal region outperform dense LLMs of identical total parameter count, training compute, and data budget, with the optimal region consistent across scales.
-
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
-
A3 : an Analytical Low-Rank Approximation Framework for Attention
A3 splits Transformer layers into QK, OV, and MLP components and derives analytical low-rank approximations that reduce hidden dimensions while minimizing each component's functional loss, yielding better perplexity than prior low-rank methods on LLaMA models.
-
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Applying a head-specific sigmoid gate after SDPA in LLMs boosts performance and stability by adding non-linearity and query-dependent sparse modulation while reducing attention sinks.
-
Improved Mean Flows: On the Challenges of Fastforward Generative Models
Improved MeanFlow (iMF) reaches 1.72 FID on ImageNet 256x256 with one function evaluation by reformulating the training objective as a regression on instantaneous velocity and treating guidance as flexible conditioning variables.
-
Rethinking Generative Image Pretraining: How Far Are We From Scaling Up Next-Pixel Prediction?
Scaling experiments on autoregressive next-pixel Transformers at 32x32 show task-dependent optimal data-to-model ratios and project compute as the dominant bottleneck for future high-resolution feasibility.
-
gpt-oss-120b & gpt-oss-20b Model Card
OpenAI releases two open-weight reasoning models, gpt-oss-120b and gpt-oss-20b, trained via distillation and RL with claimed strong results on math, coding, and safety benchmarks.
-
Hierarchical Reasoning Model
HRM is a recurrent architecture with high-level planning and low-level execution modules that reaches near-perfect accuracy on complex Sudoku, maze navigation, and ARC benchmarks using 27M parameters and 1000 samples without pre-training or CoT supervision.
-
Lightweight Domain Adaptation of a Large Language Model for Legal Assistance in the Indian Context
An 8B Llama model with RAG and prompt engineering scores 60.08% on the All-India Bar Examination, slightly above GPT-3.5 Turbo while claiming 22 times greater parameter efficiency via a new PEI metric.
-
Emerging Properties in Unified Multimodal Pretraining
BAGEL is a unified decoder-only model that develops emerging complex multimodal reasoning abilities after pretraining on large-scale interleaved data and outperforms prior open-source unified models.
-
Predicting one-year clinical instability and mortality in heart failure patients using sequence modeling
Sequence models on EHR data from a Swedish heart failure cohort achieve AUPRCs of 0.555 to 0.854 for one-year instability and mortality predictions and support four care pathways.
-
Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
This work systematically compares inter-layer and intra-layer hybridization strategies for combining self-attention and Mamba-style state space models, evaluating them on language modeling, downstream tasks, long-context performance, scaling, and efficiency to derive optimal design recipes.
- Scaling Latent Reasoning via Looped Language Models