{"total":62,"rows":[{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374,"area":"lr"},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2501.00663","title":"Titans: Learning to Memorize at Test Time","created":"2024-12-31","cited_by_count":328,"area":"lr"},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2408.05646","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","created":"2024-08-10","cited_by_count":72,"area":"lr"},{"id":"2404.05567","title":"Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models","created":"2024-04-08","cited_by_count":42,"area":"lr"},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"id":"2505.10475","title":"Parallel Scaling Law for Language Models","created":"2025-05-15","cited_by_count":30,"area":"lr"},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2409.13035","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","created":"2024-09-19","cited_by_count":22,"area":"lr"},{"id":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"id":"2509.23184","title":"PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space","created":"2025-09-27","cited_by_count":16,"area":"lr"},{"id":"2605.11011","title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","created":"2026-05-10","cited_by_count":15,"area":"lr"},{"id":"2312.15230","title":"PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs","created":"2023-12-23","cited_by_count":14,"area":"lr"},{"id":"2411.03519","title":"AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution","created":"2024-11-05","cited_by_count":14,"area":"lr"},{"id":"2506.12963","title":"Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills","created":"2025-06-15","cited_by_count":14,"area":"lr"},{"id":"2506.01115","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2406.02106","title":"MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset","created":"2024-06-04","cited_by_count":11,"area":"lr"},{"id":"2410.02102","title":"Racing Thoughts: Explaining Contextualization Errors in Large Language Models","created":"2024-10-02","cited_by_count":11,"area":"lr"},{"id":"2507.06607","title":"Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation","created":"2025-07-09","cited_by_count":11,"area":"lr"},{"id":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2408.11815","title":"Great Memory, Shallow Reasoning: Limits of $k$NN-LMs","created":"2024-08-21","cited_by_count":8,"area":"lr"},{"id":"2604.07955","title":"Rethinking Residual Errors in Compensation-based LLM Quantization","created":"2026-04-09","cited_by_count":7,"area":"lr"},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"area":"lr"},{"id":"2305.11461","title":"Hint of Pseudo Code (HoPC): Zero-Shot Step by Step Pseudo Code Reasoning Prompting","created":"2023-05-19","cited_by_count":5,"area":"lr"},{"id":"2512.19171","title":"JEPA-Reasoner: Decoupling Latent Reasoning from Token Generation","created":"2025-12-22","cited_by_count":5,"area":"lr"},{"id":"2505.21670","title":"Rethinking the Outlier Distribution in Large Language Models: An In-depth Study","created":"2025-05-27","cited_by_count":4,"area":"lr"},{"id":"2602.08220","title":"Pretraining with Token-Level Adaptive Latent Chain-of-Thought","created":"2026-02-09","cited_by_count":4,"area":"lr"},{"id":"2510.00028","title":"Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2507.20613","title":"Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression","created":"2025-07-28","cited_by_count":2,"area":"lr"},{"id":"2512.25026","title":"Modeling Language as a Sequence of Thoughts","created":"2025-12-31","cited_by_count":2,"area":"lr"},{"id":"2602.17691","title":"Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering","created":"2026-02-06","cited_by_count":2,"area":"lr"},{"id":"2604.24938","title":"Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning","created":"2026-04-27","cited_by_count":2,"area":"lr"},{"id":"2210.06376","title":"Probing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary","created":"2022-10-12","cited_by_count":1,"area":"lr"},{"id":"2406.13621","title":"LaMI: Augmenting Large Language Models via Late Multi-Image Fusion","created":"2024-06-19","cited_by_count":1,"area":"lr"},{"id":"2501.09107","title":"Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach","created":"2025-01-15","cited_by_count":1,"area":"lr"},{"id":"2505.23790","title":"Rethinking the Understanding Ability across LLMs through Mutual Information","created":"2025-05-25","cited_by_count":1,"area":"lr"},{"id":"2508.06974","title":"Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models","created":"2025-08-09","cited_by_count":1,"area":"lr"},{"id":"2510.05125","title":"Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation","created":"2025-09-30","cited_by_count":1,"area":"lr"},{"id":"2602.09442","title":"Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2602.14649","title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2605.06997","title":"Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.08755","title":"LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2605.30641","title":"COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models","created":"2026-05-28","cited_by_count":1,"area":"lr"},{"id":"2606.02559","title":"From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2608.21308","title":"Rethinking Expressivity and Efficiency in Test-Time Training","created":"2026-08-21","cited_by_count":1,"area":"lr"},{"id":"2508.19271","title":"Rethinking Reasoning in LLMs: Neuro-Symbolic Local RetoMaton Beyond ICL and CoT","created":"2025-08-22","cited_by_count":0,"area":"lr"},{"id":"2511.19496","title":"Xmodel-2.5: 1.3B Data-Efficient Reasoning SLM","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2512.21651","title":"Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models","created":"2025-12-25","cited_by_count":0,"area":"lr"},{"id":"2604.08872","title":"How does Chain of Thought decompose complex tasks?","created":"2026-04-10","cited_by_count":0,"area":"lr"},{"id":"2606.19350","title":"Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2607.18199","title":"PPL-Factory: Task-Aware and Budget-Aware Data Selection from Language Modeling to Reasoning","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.10537","title":"Measuring Semantic Abstractness of SAE Features via Nonlocality","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.17950","title":"Do Large Language Models Play Six Degrees of Separation? Measuring Topological Compression in Long-Context Manifolds","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2610.00983","title":"The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.06833","title":"Towards Looped Models Done Right, Part II: Rethinking at Fixed Points","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.09003","title":"Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.12304","title":"Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}