conftrace_

← Optimization & Theory

Deep Learning › Optimization & Theory ›

Efficient Computing

1,579 papers

Papers per year

2

1

3

4

11

7

14

32

73

87

135

160

201

191

274

322

62

'15

'20

'25

Papers

Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning ACL 2026

RoBSA: RoPE-based Blockwise Sparse Multi-head Latent Attention ACL 2026

ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval ACL 2026

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification ACL 2026

Native Hybrid Attention for Efficient Sequence Modeling ACL 2026

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding ACL 2026

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs ACL 2026

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference ACL 2026

GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models ACL 2026

Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification ACL 2026

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention ACL 2026

Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing ACL 2026

RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents ACL 2026

HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding ACL 2026

HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference ACL 2026

Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models ACL 2026

SpiderFlow: Efficient Topology-Aware Scheduling for LLM Training Across Decentralized GPU Clusters ACL 2026

Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR ACL 2026

Hyperion: Private Token Sampling with Homomorphic Encryption ACL 2026

Single-Pass, Depth-Selective Reading for Multi-Aspect Sentiment Analysis ACL 2026

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026

TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models ACL 2026

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning ACL 2026

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism ACL 2026

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring ACL 2026