Efficiency

Route Anything presents a unified theory and omni-modal trajectory matrix for routing among models, tools, and policies, finding a 5.4-point per-input oracle gap, modest learned-router gains, and 8.82× average efficiency from cheaper routes.

ParetoSaddler separates intermediate Pareto-aware promotion from final deployment selection, improving quality and reducing cost on ClawMark and GAIA2.

SpecPilot is an autonomous agentic loop that uses a ceiling-based cost model, parallel coding agents, stock-calibrated token forcing and a structured memory to discover lossless algorithms and systems optimizations for speculative decoding deployments, raising speedup over AR from 4.46× to 10.87× with one request and from 1.94× to 3.93× with batching.

Wave Forcing co-designs causal wavefront generation, three-stage training, and Wave Runtime to stream video at one chunk per concurrent forward round after pipeline fill while retaining all denoising updates.

Order-Only On-Policy Distillation trains a student to match the teacher’s ordering of top-K tokens at student-generated prefixes, avoiding teacher probability values and temperature tuning.

FLAMIA is a family of Blackwell attention kernels with MXFP8 and mixed NVFP4/FP8 training paths that use token-block scaling, causal-leakage safeguards, forward-backward numerical consistency, and GPU-side scheduling of packed documents, achieving 1.10–1.40× (B200) and 1.06–1.42× (B300) speedups on combined forward and backward attention calls.

DecisionRank trains a single-pass decision reranker by combining offline RankNet supervision with item-space on-policy distillation from a generative teacher that provides conditional feedback over candidate items.

The paper argues a qualified yes: co-designing a lightweight System-1 predictor with a costly System-2 executor can reduce execution compute toward 1/ρ_u where interactions are costly, unevenly informative, and predictable before execution.

OSWAM learns compact imagination tokens from a video DiT as structured start points for a one-step action DiT denoising, achieving competitive planning and manipulation results with 1 action denoising step and substantially lower latency than multi-step world action models.

GLOW-FM is a one-step latent flow-matching framework for low-light image enhancement that uses Terminal Velocity Matching in a frozen Tiny-VAE latent space and requires a single function evaluation.

IDM keeps the full internal DMD correction and adds a feature-moment loss on generator EMA features, improving 2-NFE LongText scores on Z-Image-Turbo and Qwen-Image.

LOWN uses a cheap TEXT-ONLY forward to certify the latest image-conditioned predictions and runs the image-conditioned FULL forward only when the certified prefix is too short, retaining 99.6% of LLaDA-V's score at 35.3% of decoding FLOPs.

SpecSlot decouples output detail from global attention by splitting a fixed token budget into spatial anchors and spectral slots, sending only the lowest-radial slot per anchor through global blocks.

CoSTA decouples an SDM's generation and synthesis token spaces by extending the generation vocabulary with BPE-compressed speech units, adapting the model, and deterministically expanding generated units back before the unchanged decoder, yielding about 1.7× speech-token generation speed.

Soft-MTP removes the noisy residual from the standard multi-token prediction gradient by recovering the KL self-distillation gradient exactly from existing cross-entropy computations, improving NTP, speculative decoding, and zero-shot accuracy without added cost.

Glance equips a single resident 9B generator backbone with a lightweight decision adapter and pointer head to rerank candidate passages from one shared prefill and then generate answers with the same backbone.

TAO jointly evaluates tool-return readiness, time-decayed KV-cache credit, and token footprint, then uses dynamic programming to select and place waiting agent sessions on GPU nodes.

A two-stage paradigm where autoregressive pretraining on semantic tokens acquires visual knowledge and a frozen-backbone pixel-diffusion stage renders images, yielding a 3B text-to-image model trained in about 6,600 H100 GPU-hours that scores 0.86 on GenEval and 87.78 on DPG-Bench.