Spoken Language Understanding papers, 2023–2026

Key findings

• Spoken Language Understanding went from 40 papers in 2023 to 61 in 2026, roughly 1.5x in three years.
• CVPR publishes the most Spoken Language Understanding work: 62 papers from 2023 to 2026, 33% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 3 in 2023 to 14 in 2026.
• Among the 5 topics under Audio and Speech, it ranks #4 by 2026 paper count; the fastest grower in the group, Audio Generation, is up 4.3x versus 1.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
• ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
• ICLR 2026Neuron-Level Analysis of Cultural Understanding in Large Language Models
• CVPR 2026Consistent Instance Field for Dynamic Scene Understanding
• NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
• ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
• ICLR 2025Toward Understanding In-context vs. In-weight Learning
• CVPR 2025HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
• NeurIPS 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
• ICML 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
• ICLR 2024Understanding Addition in Transformers
• CVPR 2024SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
• NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
• ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
• ICLR 2023Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks
• CVPR 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
• NeurIPS 2026EmbodiedObject: All-in-One Object Understanding with SLAT
• ICML 2026Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
• ICLR 2026Towards Understanding the Shape of Representations in Protein Language Models
• CVPR 2026Lifting Unlabeled Internet-level Data for 3D Scene Understanding

All Spoken Language Understanding papers

55 papers, page 1 of 2

1. NeurIPS 2026Beyond Oversquashing: Understanding Signal Propagation in GNNs Via Observables
2. NeurIPS 2026Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding
3. NeurIPS 2026Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
4. NeurIPS 2026EmbodiedObject: All-in-One Object Understanding with SLAT
5. NeurIPS 2026Emergent Semantic Role Understanding in Language Models
6. NeurIPS 2026Evaluating Multimodal Narrative Understanding of Popular Hollywood Films
7. NeurIPS 2026Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
8. NeurIPS 2026Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering
9. NeurIPS 2026RAVEN-Bench: A Paired EO-IR Video QA Benchmark for Aerial Multimodal Understanding
10. NeurIPS 2026SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding
11. NeurIPS 2026Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
12. NeurIPS 2026StakeBench: Evaluating Language Understanding Grounded in Market Commitment
13. NeurIPS 2026TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios
14. NeurIPS 2026U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
15. NeurIPS 2026Understanding axial attention in TSFMs through single location regression
16. NeurIPS 2026Understanding Circulant Permutation to Extend the CMinHash Estimator
17. NeurIPS 2026Understanding Double Descent through Universal Compression
18. NeurIPS 2026Understanding Layer Patching in Model Size Interpolation
19. NeurIPS 2026Understanding Sample Efficiency in Predictive Coding
20. NeurIPS 2026Understanding the Co-evolutionary Solution Exchange of the MOEA/D: Minimal Communication Gives Maximal Speed-Ups
21. NeurIPS 2026Understanding the Convergence of Direct Training of SNNs with Surrogate Gradients
22. NeurIPS 2026Understanding the Curse of Unrolling
23. NeurIPS 2026Understanding the Effects of Hyper-Connections on Self-Attention Dynamics: A Bifurcation Analysis
24. NeurIPS 2026ViMU: Benchmarking Video Metaphorical Understanding
25. NeurIPS 2026When Safety Becomes An Outlier: Understanding the Retention of LLM Safety Behaviors
26. NeurIPS 2025FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
27. NeurIPS 2025Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
28. NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
29. NeurIPS 2025Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
30. NeurIPS 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
31. NeurIPS 2025Towards a Geometric Understanding of Tensor Learning via the t-Product
32. NeurIPS 2025Towards Understanding Transformers in Learning Random Walks
33. NeurIPS 2025Understanding Adam Requires Better Rotation Dependent Assumptions
34. NeurIPS 2025Understanding Bias Terms in Neural Representations
35. NeurIPS 2025Understanding Differential Transformer Unchains Pretrained Self-Attentions
36. NeurIPS 2025Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability
37. NeurIPS 2025Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
38. NeurIPS 2025Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
39. NeurIPS 2025Understanding while Exploring: Semantics-driven Active Mapping
40. NeurIPS 2024E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
41. NeurIPS 2024FineCLIP: Self-distilled Region-based CLIP for Better Fine-grained Understanding
42. NeurIPS 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
43. NeurIPS 2024SILENCE: Protecting privacy in offloaded speech understanding on resource-constrained devices
44. NeurIPS 2024Understanding Emergent Abilities of Language Models from the Loss Perspective
45. NeurIPS 2024When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
46. NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
47. NeurIPS 2023Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities
48. NeurIPS 2023From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader
49. NeurIPS 2023InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
50. NeurIPS 2023NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

FAQ

How many Spoken Language Understanding papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

189 in total: 40 in 2023, 38 in 2024, 50 in 2025, 61 in 2026.

How many Spoken Language Understanding papers are at NeurIPS 2026?

NeurIPS 2026 has 25 Spoken Language Understanding papers, versus 14 the year before.

How many Spoken Language Understanding papers are at ICLR 2026?

ICLR 2026 has 6 Spoken Language Understanding papers, versus 7 the year before.

How many Spoken Language Understanding papers are at ICML 2026?

ICML 2026 has 12 Spoken Language Understanding papers, versus 10 the year before.

How many Spoken Language Understanding papers are at CVPR 2026?

CVPR 2026 has 18 Spoken Language Understanding papers, versus 19 the year before.

Which conference publishes the most Spoken Language Understanding papers?

CVPR, with 62 papers from 2023 to 2026.