ER @ NeurIPS

159 papers92 directions

Papers by Year

2026 1
2025 159

Top Research Directions

Research directions most represented by papers from this venue.

Mitigating Computational Overthinking in Large Reasoning Models 6
Optimizing Inference Length in Large Reasoning Models 3
Cross Domain Generalization of Advanced Reasoning Frameworks 3
Mitigating the Inference Latency of Chain of Thought 3
Adaptive Reasoning Depth for Language Models 2
Speculative Decoding for Autoregressive Models 2
Linear Complexity Attention for Sequence Modeling 2
Confidence Based Early Exiting for Efficient Inference 2
The Spatial Reasoning Bottleneck in Multimodal Models 2
Accelerating Sparse Neural Networks on Dense Hardware 2
Bias Inheritance in Knowledge Distillation 2
Error Propagation in Autoregressive Sequence Generation 2
Managing Visual Token Redundancy in Multimodal Models 2
The Computational Overhead of Generative Data Synthesis 2
Overcoming the Computational Cost of Transformer Architectures 2

Top Authors

AuthorPapers
Kevin Zhu5
Chengsong Huang3
Chenyu Wang3
Huaxiu Yao3
Jason E Weston3
Jiawei Zhao3
Jieyu Zhao3
Yuandong Tian3
Alessandro Achille2
Anisha Gunjal2
Aram Galstyan2
Ashwinee Panda2
Beidi Chen2
Cai Zhou2
Chelsea Finn2
DiJia Su2
Dimitris Papailiopoulos2
Dinghuai Zhang2
Elaine Lau2
Fatih Porikli2

Impactful Papers

Papers from this venue that shaped research clusters.

Foundational

Influential

Related Venues

Venues with the most similar research cluster distributions.

Papers

TitleYear
One Sample to Rule Them All: Extreme Data Efficiency in RL Scaling2025
On the Role of Temperature Sampling in Test-Time Scaling2025
On the Rollout-Training Mismatch in Modern RL Systems2025
Optimal Self-Consistency for Efficient Reasoning with Large Language Models2025
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs2025
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction2025
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning2025
Pay-Per-Search Models are Abstention Models2025
Performative Thinking? The Brittle Correlation Between CoT Length and Problem Complexity2025
PosS:Position Specialist Generates Better Draft for Speculative Decoding2025
ProRefine: Inference-time Prompt Refinement with Textual Feedback2025
Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?2025
RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm2025
RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling2025
Reasoning-Focused Evaluation of Efficient Long-Context Inference Techniques2025
Reasoning-Intensive Regression2025
Reasoning Models Can Be Accurately Pruned via Chain-of-Thought Reconstruction2025
Reasoning Models Reason Inefficiently2025
Reasoning Under Pressure: LLMs in Competitive Pokémon Battles2025
Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning2025
Reject Only Critical Tokens: Pivot-Aware Speculative Decoding2025
Resa: Transparent Reasoning Models via SAEs2025
RoiRL: Efficient, Self-Supervised Reasoning with Offline Iterative Reinforcement Learning2025
Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains2025
Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs2025
SATBench: Benchmarking LLMs Logical Reasoning via Automated Puzzle Generation from SAT Formulas2025
SGD-KV: Summarization Guided KV Cache Compression2025
Short-to-Long Distillation: Learning Long-Context Policies from Short-Context Supervision2025
SituationalPriv: A Context-Aware Framework for Privacy Detection and Protection in Vision-Language Models2025
Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments2025
SparseVILA-R1: Decoupling Visual Sparsity for Efficient VLM Reasoning2025
SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation2025
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models2025
SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache2025
Stable Reinforcement Learning for Efficient Reasoning2025
Statistical Early Stopping for Reasoning Models2025
Superposition Reasoning Model2025
SwiftSolve: A Self-Iterative, Complexity-Aware Multi-Agent Framework for Competitive Programming2025
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence2025
The Path Not Taken: RLVR Provably Learns Off the Principals2025
The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models2025
ThinkBrake: Mitigating Overthinking in Tool Reasoning2025
Think Straight, Stop Smart: Structured Reasoning for Efficient Multi-Hop RAG2025
Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering2025
Towards Quantifying Bias in Large Language Models2025
Training Dynamics Impact Quantization Degradation2025
Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing2025
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time2025
UniFormer: Unified and Efficient Transformer for Reasoning Across General and Custom Computing2025
Universal Properties of Activation Sparsity in Modern Large Language Models2025

« prev Page 3/4 next »