Bottlenecks

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Bottlenecks.

Period ending 2026-09-14

5 new papers

A weekly snapshot of new work published in Bottlenecks.

Inside this field

Focused directions

Focused topic

Bottlenecks

Within Bottlenecks

175 papersExplore

Focused topic

Concept Bottleneck Models

Within Bottlenecks

63 papersExplore

Focused topic

Class-Incremental Concept Bottleneck Model

Within Bottlenecks

19 papersExplore

227 papers

Latest in Bottlenecks

Browse all topics →

Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models
Jun 3, 2026Julian Skirzynski, Harry Cheon, Shreyas Kadekodi +2Class-Incremental Concept Bottleneck Model Concept Bottleneck Models
P $^2$ -DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
Jun 2, 2026Ruipeng Zhang, Zhihao Li, Haozhang Yuan +2Large Vision Language Models Perceptual Understanding
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
Jun 1, 2026Jiebin Zhang, Zhenghan Yu, Song Liu +9Speculative Decoding LLM Inference Efficiency
Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model
Jun 1, 2026Yijun Yang, Ruiqiang Xiao, Lijie Hu +4Medical Image Classification Multiple Instance Learning
HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
May 31, 2026Nasib Ullah, Jinbin Zhang, Jean Lucien Randrianantenaina +2Sparsity Multi-Label Classification
NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End Driving
May 29, 2026Jiahui Li, Jiawei Sun, Zixiang Ren +7Autonomous Driving Perception Concept Bottleneck Models
LVSA: Training-Free Sparse Attention for Long Video Diffusion
May 29, 2026Gael Glorian, Ioannis Lamprou, Zhen Zhang +2Dynamic Sparse Attention Bottlenecks
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
May 29, 2026Yujie Wang, Siwei Chen, Longzan Luo +4Autoregressive Rollout Long-Tailed Distribution
No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
May 28, 2026Lixuan Guo, Yifei Wang, Tiansheng Wen +3Retrieval Layer K-Means
CB-SLICE: Concept-Based Interpretable Error Slice Discovery
May 28, 2026Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud +1Concept Bottleneck Models Slices
HTAM: Hierarchical Transition-Attended Memory for Operator Optimization
May 28, 2026Yining Zhang, Mingyang Yi, Chen Wang +5Code Optimization Large Language Model Serving
PRO-CUA: Process-Reward Optimization for Computer Use Agents
May 27, 2026Yifei He, Rui Yang, Hao Bai +2Reliable Medical Process-Level Reward Model Evaluation Framework Agentic Reinforcement-Learning Framework
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
May 27, 2026Hao Jiang, Shurui Li, Tianpeng Bu +7Multi-Objective Policy Optimization Exploration-Exploitation Dilemma
STAB: Specification-driven Testing for Algorithmic Bottlenecks
May 27, 2026Soohan Lim, Joonghyuk Hahn, Hyundong Jin +1Test Generation Bottlenecks
EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
May 27, 2026Yunqi Liu, Tong Niu, Zitong Wang +4Multimodal Agents Agentic Benchmarks
Why Can't They Remember? Uncovering Representation and Retrieval Bottlenecks in Multi-Turn Acoustic Memory
May 26, 2026Yang Xiao, Siyi Wang, Han Yin +4Large Audio Language Models Large Language Model Memory
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
May 26, 2026Xiaochong Jiang, Shiqi Yang, Ziwei Li +3Bottlenecks Token Budgets
GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization
May 25, 2026Maoyang Xiang, Tao Luo, Bo WangQuantization Flexible Register Transfer Level Design Automation
Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning
May 25, 2026Aleksandar Todorov, Matthia SabatelliBottlenecks
Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
May 25, 2026Yiwei Xie, Ping Liu, Zheng ZhangConcept Erasure Video-Text Alignment
When Interpretability Becomes a Liability: Adversarial Attacks on CBM Concept Layers
May 25, 2026Aditya SridharConcept Bottleneck Models Model Interpretability
Clarification Is Not Enough: Post-Clarification Answering Remains the Bottleneck in Multi-Turn QA
May 24, 2026Jinyan Su, Jennifer HealeyMultimodal Query Pluralistic Alignment
WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
May 23, 2026Jiangnan Yu, Kisson Songqi Lin, Jilong WuLarge Language Model Memory Long-Term Memory
ConceptM $^3$ oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology
May 23, 2026Xuan Wang, Zhongling Xu, Gopi Kannedhara +13Pathology Foundation Models Multimodal Clinical Data
Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmarks
May 22, 2026Ashok Chandrasekar, Jason KrambergerPer-Token Latency LLM Inference Efficiency
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
May 22, 2026Bowen Duan, Cong Guo, Chiyue Wei +8Calibration-Free Low-Bit Vector Quantization Extreme Low-Bit Quantization
Hoeffding Concept Bottleneck Models with Applications to Overhead Images
May 22, 2026Clément Bénard, Manon Arfib, Christophe Labreuche +1Class-Incremental Concept Bottleneck Model Concept Bottleneck Models
DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in Open-World Object Detection
May 22, 2026Yingjun Xiao, Xi Chen, Gang Fang +1Open-Vocabulary Object Detection Duality
Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
May 21, 2026Julian Gutheil, Simon Hitzginger, Robert LegensteinActivation Functions Multi--Task Learning
Diagnosis Is Not Prescription: Linguistic Co-Adaptation Explains Patching Hazards in LLM Pipelines
May 21, 2026Yoon Jeonghun, Kim DongchanLarge Language Model Performance Large Language Model Pipelines
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
May 20, 2026Hangyu Lin, Chao Wen, Chengming Xu +4Multimodal Alignment Ava-Vlm
Matryoshka Concept Bottleneck Models
May 20, 2026Ziye Chen, Hongbin Lin, Jie Li +1Class-Incremental Concept Bottleneck Model Concept Bottleneck Models
TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload
May 19, 2026Zhiben Chen, Youpeng Zhao, Yang Sui +2Bottlenecks
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs
May 19, 2026Haiquan Lu, Zigeng Chen, Gongfan Fang +2LLM Inference Efficiency Prefill
Structured Layout Priors for Robust Out-of-Distribution Visual Document Understanding
May 19, 2026Peter El Hachem, Ahmed Nassar, A. Said Gurbuz +2Visual Document Retrieval Discrete Tokens
CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models
May 19, 2026Yike Sun, Mingkun Xu, Mu You +5Model Interpretability Efficient Influence Function
AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
May 19, 2026Ziye Chen, Hongbin Lin, Chenyu Zhang +3Low-Rank Adaptation Zeroth-Order Optimization
Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers
May 19, 2026Xinzhe Yuan, Xiang Peng, Bin Gu +1Spiking Neural Networks Neuromorphic Hardware
Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
May 18, 2026Bryce Hinkley, Peyman NajafiradDiffusion Editing Refusals
The Symmetries of Three-Layer ReLU Networks
May 18, 2026Johanna Marie Gegenfurtner, Moritz Grillo, Guido MontúfarRectified Linear Unit Networks Symmetry
AdaptiveLoad: Towards Efficient Video Diffusion Transformer Training
May 18, 2026Yucheng Guo, Yongjian Guo, Zhong Guan +6Pre-Trained Video Diffusion Models Generative Image Compression
ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
May 17, 2026Mingyang Rao, Kehua Feng, Zhihui Zhu +4Vast Chemical Space Reaction
Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search
May 15, 2026Sarah Martinson, Michael P. Brenner, Martyna Plomecka +3Epidemic Forecasting Clinical Prediction
When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing
May 15, 2026Libo Sun, Po-wei Harn, Peixiong He +1Mixture-of-Experts Models Imagenet
KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
May 14, 2026Yingbing Huang, Tharun Adithya Srikrishnan, Steven K. Reinhardt +1Key-Value Cache Compression Autoregressive Decoding
Exploring Bottlenecks in VLM-LLM Navigation: How 3D Scene Understanding Capability Impacts Zero-Shot VLN
May 14, 2026Ziyi Xia, Chaoran Xiong, Litao Wei +2Vision-Language Navigation 3D Scene Understanding
Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners
May 14, 2026Qingyang Liu, Bingjie Gao, Canmiao Fu +9Unified Multimodal Models Visual Reasoning
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
May 14, 2026Langzhou He, Junyou Zhu, Yue Zhou +7Agentic Reinforcement-Learning Framework Token-Level Uncertainty
Towards Fine-Grained and Verifiable Concept Bottleneck Models
May 14, 2026Yingying Fang, Haijie Xu, Shuang Wu +2Class-Incremental Concept Bottleneck Model Concept Bottleneck Models
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
May 13, 2026Zedong Liu, Xinyang Ma, Dejun Luo +9Key-Value Cache Compression Large Language Model Serving
Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
May 13, 2026Nicola Debole, Andrea Passerini, Stefano Teso +2Concept Bottleneck Models Annotations
When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
May 13, 2026John Lazarsfeld, Anas Barakat, Georgios Piliouras +2Convergence Analysis Imperfect-Information Games
Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling
May 13, 2026Adil AminLarge Models Scaling Laws
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
May 12, 2026Sanah Suri, Kieran Ringel, Maike SonnewaldClass-Incremental Concept Bottleneck Model Ocean
CATS: Cascaded Adaptive Tree Speculation for Memory-Limited LLM Inference Acceleration
May 11, 2026Yuning Han, Yangchenchen Jin, Dylan Zhao +1Speculative Decoding LLM Inference Efficiency
SLASH the Sink: Sharpening Structural Attention Inside LLMs
May 11, 2026Yiming Liu, Bin Lu, Xinbing Wang +2Concept Bottleneck Models Sharpness-Aware Minimization
Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
May 11, 2026Dario VajdaGraph-Based Retrieval Augmented Generation Graph Language Models
TopoU-Net: a U-Net architecture for topological domains
May 11, 2026Gaurav Gaurav, Ibrahem ALJabea, Yaroslav Zakomornyy +4U-Net Hypergraphs
DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
May 10, 2026Zhichen Zeng, Chi-Chih Chang, Jiayi Wang +10Mixture-Of-Expert Inference Mixture-of-Experts Models
Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)
May 9, 2026Ankit Hemant Lade, Sai Krishna Jasti, Indar Kumar +1Bottlenecks Sample Size

Jun 3, 2026 · cs.LGJ/K move · Enter open · S save

Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models

Julian Skirzynski, Harry Cheon, Shreyas Kadekodi, Meredith Stewart+1

University of California, San Diego

Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels. This limits researchers' ability to determine which problems are suitable for these models, isolate the factors that drive their performance or lead to failures, or uncover which algorithms perform well. In this paper, we develop synthetic benchmarks for concept-bottleneck models, focusing on their two main use cases: decision support, in which models assist humans in making better decisions, and automation, in which models handle routine tasks without supervision. Our benchmarks can generate labeled datasets while controlling for properties that affect performance, including data modality, concept choice, annotation quality, and completeness. We demonstrate how the benchmarks can be used to evaluate representative classes of concept bottleneck models. Our demonstrations show how the benchmarks can diagnose failure modes and guide follow-up testing.

Class-Incremental Concept Bottleneck Model Concept Bottleneck Models Decisions

Open paper Ask about it PDF