VideoMLA applies multi-head latent attention with 3D-RoPE decoupling to autoregressive video diffusion, delivering 92.7% KV memory reduction while matching short-horizon baselines and leading long-horizon VBench scores.
super hub Mixed citations
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Mixed citation behavior. Most common role is background (70%).
144
Pith papers citing it
Background
70% of classified citations
abstract
We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.
hub tools
citation-role summary
background 24
method 5
dataset 3
baseline 1
citation-polarity summary
claims ledger
- abstract We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSe
authors
co-cited works
representative citing papers
LiveBench is a contamination-limited LLM benchmark with auto-scored challenging tasks from recent sources across math, coding, reasoning and more, where top models score below 70%.
CrossPool separates weights and KV-cache into distinct GPU pools plus a planner, virtualizer, and layer-wise scheduler to cut P99 time-between-tokens by up to 10.4x versus prior kvcached multi-LLM systems.
LazyAttention kernelizes deferred positional encoding to enable zero-copy, position-agnostic KV cache reuse, delivering 1.37× lower TTFT and 1.40× higher throughput than Block-Attention under skewed document distributions while preserving output quality.
Training-free looped transformers retrofit recurrence to frozen models via damped ODE sub-steps on mid-stack blocks, yielding gains such as +2.64 pp on MMLU-Pro for Qwen3-4B.
Latent Cache Flow uses a small joint-translation-and-compression adapter to let LLMs with different contexts exchange KV cache summaries, outperforming both larger C2C adapters and text in early experiments.
Text2CAD-Bench supplies 600 dual-prompt examples across four geometric and domain levels to test LLMs on text-to-parametric CAD, finding solid basic performance but sharp drops on complex topology and advanced features.
LLMForge is a NAS framework with Infinite-Head Attention, a Forge-Former surrogate, and Forge-DSE engine that discovers hardware-specific architectures for edge language models, yielding variants with improved accuracy, energy, or latency on different substrates.
φ-balancing is a convex optimization method for population-level expert balance in MoE training that derives an online EMA adjustment and outperforms heuristic baselines.
GQLA exposes dual MQA-absorb and GQA decoding paths from identical parameters to enable hardware-adaptive LLM inference while preserving cache compression on one path and GQA-level traffic on the other.
MSD eliminates dequantization from the GEMM path by decomposing BF16 activations into multiple low-precision parts that multiply directly with INT8 or MXFP4 weights, achieving near-16 effective bits for INT8 and 6.6 for MXFP4 with reduced HBM traffic.
Power capping is illusory in LLM decode as memory-bound operation leaves power headroom untouched on 700 W GPUs, while SM clock locking saves up to 32% energy and three DVFS classes appear across attention types.
EEP makes wide expert-parallel MoE serving survive single-rank failures with an 11s recovery pause, 8s reintegration pause, and throughput restored to 95% of pre-fault level within 52s while staying within 4.4% of a fixed-membership baseline in steady state.
Fully Looped Transformer stabilizes looped training up to 12 iterations via distributed inter-loop signals and attention injection, improving downstream performance by up to 13.2%.
Standard top-k routers in MoE language models often select suboptimal routes for difficult tokens, and updating only the final router layer raises pass@K on AIME and HMMT benchmarks across multiple models.
KernelBenchX benchmark shows task category explains nearly three times more variance in LLM kernel correctness than method choice, iterative refinement boosts correctness but reduces performance, and quantization remains unsolved.
Misrouter enables input-only attacks on MoE LLMs by optimizing queries on open-source surrogates to route toward weakly aligned experts and transferring them to public APIs.
Hosted open-weight LLM APIs function as time-varying heterogeneous services rather than fixed model artifacts, with demand concentrated, supply-use mismatches, and task-specific routing yielding major cost and throughput gains.
Incompressible Knowledge Probes enable log-linear estimation of LLM parameter counts from factual accuracy on obscure questions, showing continued scaling of knowledge capacity across open and closed models.
DPC maintains exactly one DRAM copy of each file page in a CXL-connected cluster and delivers up to 12.4X speedup (5.6X geometric mean) over replicated caches on data-sharing workloads.
LLM planners for robots often produce dangerous plans even when planning succeeds, with safety awareness staying flat as model scale improves planning ability.
Counterfactual Routing awakens dormant experts in MoE models via layer-wise perturbation and a new CEI metric, raising factual accuracy 3.1% on average across TruthfulQA, FACTOR, and TriviaQA without extra inference cost.
In Kuramoto networks at equilibrium, weak nudging makes phase displacement the exact gradient of loss w.r.t. natural frequencies, enabling frequency learning that beats weight learning and resolves convergence via spectral initialization.
COVERT generates verifiable synthetic tool-use environments for RL by validated trajectory synthesis and oracle-preserving augmentations, improving tool-use accuracy on BFCL v3 and ACEBench while remaining complementary to SFT.
citing papers explorer
-
Search Your Block Floating Point Scales!
ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.
-
PowerStep: Memory-Efficient Adaptive Optimization via $\ell_p$-Norm Steepest Descent
PowerStep delivers coordinate-wise adaptive optimization by nonlinearly transforming a momentum buffer under an lp-norm steepest-descent geometry, matching Adam convergence with half the memory and supporting aggressive quantization.
-
From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay
NSER uses zero-shot LLMs to induce behavioral rules from RL trajectories, grounds them in differentiable first-order logic, and applies the symbolic structures to dynamically reweight experience replay for better sample efficiency.
-
LBI: Parallel Scan Backpropagation via Latent Bounded Interfaces
LBI enables tractable parallel backpropagation by reducing inter-region adjoint computation to low-dimensional r x r Jacobians while preserving exact gradients under a bounded-interface model.
-
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
OTora is a two-stage framework that generates insertion-aware adversarial triggers and ICL-guided genetic payloads to induce reasoning-level denial-of-service in tool-augmented LLM agents across multiple backbones while preserving task correctness.
-
Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
MELT decouples reasoning depth from memory in looped language models by sharing a single gated KV cache per layer and training it via chunk-wise distillation from Ouro starting models.
-
UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
A shared global expert pool in MoE improves validation loss over per-layer experts and allows sublinear expert-parameter growth with depth.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
MoE-Hub: Taming Software Complexity for Seamless MoE Overlap with Hardware-Accelerated Communication on Multi-GPU Systems
MoE-Hub enables seamless MoE communication overlap via hardware-accelerated destination-agnostic data transmission, delivering 1.40x-3.08x per-layer and 1.21x-1.98x end-to-end speedups over prior systems.
-
Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism
Nitsum dynamically adapts tensor parallelism and GPU splits in LLM serving to raise SLO-compliant goodput by up to 5.3 times over prior systems.
-
The Impossibility Triangle of Long-Context Modeling
No model can achieve efficiency, compactness, and recall capacity scaling with sequence length at once, as any two imply a strict bound of O(poly(d)/log V) on recallable facts.
-
A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
A queueing model derives stability conditions for LLM inference services under combined compute and KV cache memory limits, with experimental validation showing typical deviations under 10%.
-
DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
DITRON introduces a hierarchical multi-level tiling compiler for distributed tensor programs that matches or exceeds expert CUDA libraries with 6-30% speedups and has been deployed to improve training MFU by over 10% while saving hundreds of thousands of GPU hours monthly.
-
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
A disagreement-guided routing framework dynamically selects among resolution, voting, and rewriting strategies for test-time scaling, delivering 3-7% accuracy gains with lower sampling cost on mathematical benchmarks.
-
Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
HyLo upcycles Transformer LLMs into hybrids with MLA and Mamba2/Gated DeltaNet blocks via staged training and distillation, extending context to 2M tokens and outperforming prior upcycled hybrids on long-context benchmarks.
-
Mixture of Heterogeneous Grouped Experts for Language Modeling
MoHGE achieves standard MoE performance with 20% fewer parameters and balanced GPU utilization via grouped heterogeneous experts, two-level routing, and specialized auxiliary losses.
-
Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs
NPUMoE accelerates MoE LLM inference on Apple Silicon NPUs via offline-calibrated static expert tiers, grouped execution, and load-aware graph residency, delivering 1.32x-5.55x lower latency and 1.81x-7.37x better energy efficiency.
-
Multi-LLM Token Filtering and Routing for Sequential Recommendation
MLTFR combines user-guided token filtering with a multi-LLM mixture-of-experts and Fisher-weighted consensus expert to deliver stable gains in corpus-free sequential recommendation.
-
Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter
PrfaaS enables practical cross-datacenter prefill-decode disaggregation for hybrid-attention models via selective offloading, bandwidth-aware scheduling, and cache-aware placement, yielding 54% higher throughput and 64% lower P90 TTFT than homogeneous baselines in a 1T-parameter case study.
-
ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving
ELMoE-3D achieves 6.6x average speedup and 4.4x energy efficiency gain for MoE serving on 3D hardware by scaling expert and bit elasticity for elastic self-speculative decoding.
-
AsyncTLS: Efficient Generative LLM Inference with Asynchronous Two-level Sparse Attention
AsyncTLS delivers full-attention accuracy with 1.2-10x operator speedups and 1.3-4.7x end-to-end throughput gains on 48k-96k contexts via two-level sparse attention and asynchronous offloading.
-
Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
Local Platt scaling on three fine-grained confidence scores reduces calibration error for LLM-based automated code revision across tasks and models compared to global scaling alone.
-
ITIScore: An Image-to-Text-to-Image Rating Framework for the Image Captioning Ability of MLLMs
ITIScore evaluates MLLM image captions via image-to-text-to-image reconstruction consistency and aligns with human judgments on a new 40K-caption benchmark.
-
WIO: Upload-Enabled Computational Storage on CXL SSDs
WIO enables reversible computational storage on CXL SSDs via WebAssembly actors and zero-copy migration, achieving up to 2x throughput and 3.75x lower write latency.
-
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
HyperP transfers optimal learning rates across model width, depth, tokens, and MoE granularity under Frobenius-sphere constraints, delivering stable scaling and 1.58x efficiency gains.
-
EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
EchoKV compresses LLM KV caches by reconstructing missing components from partial data via inter- and intra-layer attention similarities, outperforming prior methods on LongBench and RULER while supporting on-demand full-cache inference.
-
Why Attend to Everything? Focus is the Key
Focus learns a few centroids to gate long-range token attention, producing sparse attention that matches or beats full attention quality with up to 8.6x speedup at million-token lengths.
-
mHC: Manifold-Constrained Hyper-Connections
mHC projects hyper-connection residual spaces onto a manifold to restore identity mapping, enabling stable large-scale training with performance gains over standard HC.
-
Janus: Disaggregating Attention and Experts for Scalable MoE Inference
JANUS disaggregates attention and MoE layers onto separate GPU pools with an expert-balancing scheduler and SLO-aware scaling, delivering up to 4.7x higher per-GPU throughput than prior MoE systems under token-level latency constraints.
-
BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding
BLASST dynamically sparsifies attention by thresholding softmax scores to skip blocks, delivering 1.5x speedups at 70%+ sparsity while preserving benchmark accuracy.
-
Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
Seer improves synchronous LLM RL rollout throughput by up to 2.04x and reduces long-tail latency by 72-94% via divided rollout, context-aware scheduling, and adaptive grouped speculative decoding based on prompt similarity observations.
-
DeepSeek-OCR: Contexts Optical Compression
DeepSeek-OCR compresses text contexts up to 20x via 2D optical mapping while achieving 97% OCR accuracy below 10x and 60% at 20x, outperforming prior OCR tools with fewer vision tokens.
-
From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill
Layered prefill replaces token-chunked prefill with layer-group interleaving in MoE models, cutting TTFT by up to 70%, end-to-end latency by 41%, and per-token energy by 22% while preserving stall-free TBT.
-
GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference
GRACE-MoE integrates expert grouping, dynamic replication, and locality-aware routing with hierarchical sparse communication to reduce end-to-end latency in distributed SMoE inference.
-
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
EMoE trains MoE models so they maintain performance when the number of activated experts changes at inference, expanding the usable range to 2-3 times the training k with higher peak results.
-
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
MemAgent uses multi-conversation RL to train a memory agent that reads text in segments and overwrites memory, extrapolating from 8K training to 3.5M token QA with under 5% loss and 95%+ on 512K RULER.
-
Siamese Foundation Models for Crystal Structure Prediction
DAO pretrains Siamese diffusion-based models on stable/unstable crystal data to achieve 100% experimental match on Cr6Os2 and 2000x speedup over DFT on real superconductors.
-
Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
Capacity-aware dropping techniques mitigate load imbalance in MoE inference, delivering up to 1.85x speedup with 0.2% or less performance change on models including Mixtral-8x7B.
-
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
NSA is a hardware-aligned sparse attention mechanism that enables end-to-end trainable long-context modeling by combining coarse token compression with fine-grained selection.
-
Optimization Hyper-parameter Laws for Large Language Models
Opt-Laws predicts LLM final training loss from LR schedules via SDE-derived convergence and escape features, with 94% Top-2 hit rate on held-out schedules and F1=0.92 for divergence detection.
-
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Repeated sampling scales problem coverage log-linearly with sample count, improving SWE-bench Lite performance from 15.9% to 56% using 250 samples.
-
Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE Inference
CAEE reduces MoE inference latency 8-18% on 671B DeepSeek-R1 by cost-aware expert pruning and low-overhead compensation while keeping accuracy drop under 1%.
-
Conservation Laws for Modern Neural Architectures
Unified framework characterizes conservation laws for gradient flow in feedforward networks with GELU/SiLU/SwiGLU, multihead attention with positional encodings, and MoE models under various gating.
-
MiniPIC: Flexible Position-Independent Caching in <100LOC
MiniPIC enables multiple position-independent caching methods inside vLLM via unrotated KV storage, per-request RoPE application, and three primitives, delivering 49% prefill throughput gains and up to 100x lower cached-span TTFT on 2WikiMultihopQA.
-
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.
-
MESA: Improving MoE Safety Alignment via Decentralized Expertise
MESA decentralizes safety duties in MoE LLMs via expert capacity reallocation and dynamic routing refinement based on optimal transport theory, yielding robust defense on harmful benchmarks while preserving helpfulness.
-
Wall-OSS-0.5 Technical Report
Wall-OSS-0.5 is a 4B VLA model pretrained across many embodiments that achieves zero-shot real-robot performance on a 17-task suite and outperforms π_0.5 after fine-tuning.
-
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation for Efficient MoE LLM Serving
Operator-level attention-FFN disaggregation enables ~4k tokens/s throughput for DeepSeek-V3.2 under tight TTFT/TPOT SLOs where chunked-prefill and prefill-decode baselines cannot.
-
NITP: Next Implicit Token Prediction for LLM Pre-training
NITP adds dense supervision from shallow model layers to predict implicit next-token semantics, yielding consistent downstream gains on 0.5B-9B models with ~2% extra training FLOPs.
-
Instant GPU Efficiency Visibility at Fleet Scale
OFU is a hardware-counter metric that approximates application MFU to within 2 percentage points after tile correction and shows r=0.78 correlation on 608 production jobs.