Imagen de Portada

DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Xiang, Hu, Xuming, Chu, Xiaowen, Choi, Eunsol
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
por: Liu, Xiang, et al.
Publicado: (2025)

FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management
por: Liu, Xiang, et al.
Publicado: (2025)

LongGenBench: Long-context Generation Benchmark
por: Liu, Xiang, et al.
Publicado: (2024)

Improving LLM-as-a-Judge Inference with the Judgment Distribution
por: Wang, Victor, et al.
Publicado: (2025)

Learning to Reason Across Parallel Samples for LLM Reasoning
por: Qi, Jianing, et al.
Publicado: (2025)

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
por: Chen, Shuang, et al.
Publicado: (2025)

AmbigDocs: Reasoning across Documents on Different Entities under the Same Name
por: Lee, Yoonsang, et al.
Publicado: (2024)

SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
por: Chen, Hong, et al.
Publicado: (2026)

User Feedback in Human-LLM Dialogues: A Lens to Understand Users But Noisy as a Learning Signal
por: Liu, Yuhan, et al.
Publicado: (2025)

Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
por: Liu, Xiang, et al.
Publicado: (2025)

To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
por: Cheng, Wei, et al.
Publicado: (2026)

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning
por: Li, Zheng, et al.
Publicado: (2025)

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
por: Waheed, Abdul, et al.
Publicado: (2025)

The Multi-Round Diagnostic RAG Framework for Emulating Clinical Reasoning
por: Sun, Penglei, et al.
Publicado: (2025)

SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens
por: Liu, Chengbo, et al.
Publicado: (2024)

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
por: Wang, Xinglin, et al.
Publicado: (2024)

ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
por: Liao, Huanxuan, et al.
Publicado: (2026)

Are Dilemmas and Conflicts in LLM Alignment Solvable? A View from Priority Graph
por: Tang, Zhenheng, et al.
Publicado: (2026)

Efficient Vision-Language Reasoning via Adaptive Token Pruning
por: Li, Xue, et al.
Publicado: (2025)

Beyond Single Embeddings: Capturing Diverse Targets with Multi-Query Retrieval
por: Chen, Hung-Ting, et al.
Publicado: (2025)

CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning
por: Wu, Siye, et al.
Publicado: (2026)

Bridging Latent Reasoning and Target-Language Generation via Retrieval-Transition Heads
por: Patel, Shaswat, et al.
Publicado: (2026)

Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning
por: Li, Chen, et al.
Publicado: (2025)

Mitigating Temporal Misalignment by Discarding Outdated Facts
por: Zhang, Michael J. Q., et al.
Publicado: (2023)

RefreshKV: Updating Small KV Cache During Long-form Generation
por: Xu, Fangyuan, et al.
Publicado: (2024)

RedWhale: An Adapted Korean LLM Through Efficient Continual Pretraining
por: Vo, Anh-Dung, et al.
Publicado: (2024)

Open-World Evaluation for Retrieving Diverse Perspectives
por: Chen, Hung-Ting, et al.
Publicado: (2024)

InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning
por: Su, Junyou, et al.
Publicado: (2026)

ExpertFlow: Efficient Mixture-of-Experts Inference via Predictive Expert Caching and Token Scheduling
por: He, Xin, et al.
Publicado: (2024)

HAMburger: Accelerating LLM Inference via Token Smashing
por: Liu, Jingyu, et al.
Publicado: (2025)

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
por: Huang, Jianuo, et al.
Publicado: (2025)

Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
por: Huang, Yiming, et al.
Publicado: (2026)

LLM-Oriented Token-Adaptive Knowledge Distillation
por: Xie, Xurong, et al.
Publicado: (2025)

ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
por: Liang, Yesheng, et al.
Publicado: (2025)

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
por: Feng, Ruixiang, et al.
Publicado: (2026)

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
por: Liu, Hanbing, et al.
Publicado: (2025)

From Distributional to Overton Pluralism: Investigating Large Language Model Alignment
por: Lake, Thom, et al.
Publicado: (2024)

PropMEND: Hypernetworks for Knowledge Propagation in LLMs
por: Liu, Zeyu Leo, et al.
Publicado: (2025)

Rhapsody: A Dataset for Highlight Detection in Podcasts
por: Park, Younghan, et al.
Publicado: (2025)

On Language Models' Sensitivity to Suspicious Coincidences
por: Padmanabhan, Sriram, et al.
Publicado: (2025)