Tag
Bhandari et al. introduce ReadKV, storing KV caches in progressive codes to fetch precision selectively based on query attention, cutting read bandwidth by half with minimal perplexity impact.
Zhang et al. reveal that lossy speculative decoding causes jailbreak vulnerabilities to spike far faster than utility drops, introducing SecureSD with early-token stricter verification.
Myrzakhan and Shen introduce dSpark, a schedule distillation framework for diffusion LLMs that prioritizes tokens resolving global sequence uncertainty, achieving up to 10.12x speedups on reasoning benchmarks.
Ke, Cai, and Wang reveal that training instability in decoupled LLM RL pipelines stems from subtle rounding-location discrepancies across inference and training engines, demonstrating that targeted FP32 retention in RoPE, SwiGLU, and RMSNorm prevents policy collapse.
Combining stochastic depth pretraining with the BeNice post-training broadcast enables looped transformers to share KV caches across recurrences, boosting throughput by 24% and cutting p90 TTFT by 84%.
Decoupling sparse attention indexing from physical memory locations, UlaCache delivers up to 2.51x decoding throughput speedups on NVIDIA Blackwell by combining parallel bucketed LRU eviction with zero-overhead buffer retention.
By remapping tensor layouts directly during RDMA transfers, HAWK disaggregates GPU prefill and NPU decode to boost serving power efficiency by 1.26x and cost efficiency by 1.72x.
By reusing target model hidden states and eliminating the draft model's expanding historical KV cache, DLite overcomes speculative decoding degradation in multi-turn agentic environments.
By re-weighting attention logits with token importance scores, TokenGate enables end-to-end learnable token pruning over long-context inputs, reducing peak memory by 1.5x to 3.4x with zero accuracy loss.
By training a 0.62M-parameter drafter to predict position commit trajectories and introducing coupled-noise match verification, SPOT accelerates diffusion LLMs without quality loss.
A combination of hardware-model co-design, analytical zero-warmup kernel selection, and agentic code translation yields up to 1.5x throughput gains for recommendation model training on AMD Instinct MI350X accelerators.
Fused Triton autograd kernels and a host-sync-free preallocated buffer compress sparse ReLU and ReLU^2 activation caches losslessly, saving nearly a third of per-token VRAM with under 1% overhead.
Profiling remote KV caching for GLM-5.3 with MLA on 8xB300 nodes reveals cache hits were slower than recomputing; rank-partitioned sharding and async loading drop p99 tail latency from 83s to 0.67s.
An audit of the top 200 Hugging Face GGUF repositories reveals an Independent Verifiability Rate of 0/198 under standard disclosures, showing hidden compiler flags and per-tensor quantization recipes are required for bit-for-bit verification.
Staging file writes and network requests at a microVM boundary with speculative execution cuts AgentDojo prompt-injection success from 47.0% to 2.7% without degrading benign utility.
A meta-controller trained via Monte Carlo control over compact workflow states recovers 44 to 81% of the executor-advisor gap at under half the advisor cost.
Wang et al. resolve distribution shifts in Hessian-guided LLM pruning by calibrating during autoregressive decoding, pairing it with an N:M sparse matrix-vector CUDA kernel.
Li et al. identify preconditioner distortion in 4-bit AdamW quantization, proposing ZIP-SR and ZE-EDEN to cut validation loss gaps to FP32 by up to 70%.
Stanford researchers pair slow pretrained VLA proposals with high-frequency RL action edits to solve the latency lag on real robots, jumping from 42% to 97% success in 10 minutes.
What moved in 2012 was not a sudden invention of deep nets: ImageNet-scale labeled data, GPU training, ReLU, and dropout made a large ConvNet win a public, comparable benchmark-AlexNet as the ImageNet moment, not the first deep network.
The 2017 transformer reorganized sequence modeling around self-attention without recurrence; GPT and BERT are two objectives on that backbone; Kaplan and Chinchilla scaling laws are empirical regularities about compute, data, and parameters-not a slogan that bigger is always better.
An 85-task infra/eval benchmark spanning kernels, long-horizon repo work, and end-to-end optimization: topped by Claude Opus 5 at 36.53%, with a lot of headroom left.