Training Efficiency & Optimization - Weekly Roundup

HeteroFold unlocks $10.7\times$ faster cross-family KV cache transfer for LLMs, eliminating receiver prefill and matching text-based communication performance.

Control accent strength in zero-shot TTS with a single model and inference-time weight, outperforming cascaded systems on out-of-domain accents without sacrificing speaker identity.

Agents can achieve up to 5.8% higher success rates by learning a reusable "experience tree" directly from data, bypassing LLM-generated skills and enabling true generalization.

AI systems can auto-evolve by learning from their own failures, achieving 20.5% better performance with 65.5% fewer rollouts than existing methods.

This work proposes SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA), a framework incorporating Segment-Locked Credit Assignment (SLCA) that decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states.

HeteroFold unlocks $10.7\times$ faster cross-family KV cache transfer for LLMs, eliminating receiver prefill and matching text-based communication performance.

Control accent strength in zero-shot TTS with a single model and inference-time weight, outperforming cascaded systems on out-of-domain accents without sacrificing speaker identity.

Agents can achieve up to 5.8% higher success rates by learning a reusable "experience tree" directly from data, bypassing LLM-generated skills and enabling true generalization.

AI systems can auto-evolve by learning from their own failures, achieving 20.5% better performance with 65.5% fewer rollouts than existing methods.

This work proposes SLCA-GRPO, a framework incorporating Segment-Locked Credit Assignment (SLCA), a framework incorporating Segment-Locked Credit Assignment (SLCA) that decouples advantage estimation at the structural segment level within a single group of rollouts, without requiring additional rollouts from intermediate states.

Recurrent token mixing via GTR achieves 58.9 AP on COCO with sub-2ms latency, offering a practical, efficient alternative to quadratic self-attention for high-resolution dense prediction.

AURA (Angular Update Rate Adaptation), a per-parameter step-size adaptation that can be added on top of any first-order optimizer, and removed from it, without altering its update direction, is introduced.

A rigidity theorem is established: for continuous piecewise linear generators with a finite number of segments, any \(C^3\) function that can be represented in this way is at most quadratic, which demonstrates how generator dynamics and remainder estimates govern depth allocation and approximation rates of deep neural networks.

It is demonstrated that, for any $(f,\kappa)$-robust aggregator with coefficient $\kappa = O(f/n)$, where f is the number of adversarial clients and n is the total number of clients, convergence holds after an explicit sample burn-in.

It is proved that agents'parameters converge almost surely to the same limit points as in the attack-free case over time-varying communication graphs under linear parameterizations of the value and team-reward functions and Byzantine edge attacks.

This work proposes NeRF-aided Camera Ray Regression (NaCR), a unified framework that seamlessly bridges NeRF and CRR at the ray level and introduces a two-stage training curriculum to ensure stable convergence within the highly non-convex image space.

This work extends planning under a Riemannian metric from unconstrained spaces to constraint submanifolds by applying the induced metric in both a sampling-based planner and a trajectory optimizer.

DynaForge combines low-frequency global planning with high-frequency object-centric inverse kinematics across task phases, and applies a residual policy to correct actions during dynamic interaction, showing the ability of DynaForge for sim-to-real transfer.

Conduit is presented, a framework-agnostic runtime that exposes RL experience management as an explicit systems optimization problem and reduces exposed experience-path latency by up to 97% and end-to-end iteration latency by up to 38%, scales to 1,024 GPUs, and preserves convergence.

A layered visibility framework is synthesized that shows how register records reflect disclosure arrangements and why interoperability requires shared concepts, clear definitions, and preserved provenance.

The tested signature adds IID signal but shows no repeatable shift-stability advantage, demonstrating why mesoscopic graph claims need partition-matched controls and repeated null draws.

DACG-agent is presented, a drift-aware causal-graph agent that incrementally builds a causal knowledge graph from PubMed abstracts and applies a two-layer stopping policy with complementary roles: a KL-divergence monitor that detects posterior convergence (the accuracy layer), and a Bradley--Terry process reward model (PRM) whose online decline detection halts retrieval once evidence quality peaks (the efficiency layer).

This study proposes an adaptive EFL writing feedback generation framework that combines a dual-stream generative network, low-rank adaptation, and proximal policy optimization to solve the challenges of coarse intervention granularity and homogeneous feedback in EFL writing.