arXiv AI

Provably Optimal HBT Legalization in Seconds: Certified Optima Reveal Where the Headroom Really Lies

The paper presents GEO-Exact, an exact solver for Hybrid Bonding Terminal (HBT) legalization that achieves provably optimal assignments on 21 benchmark instances. It demonstrates that existing heuristics, including a reinforcement‑learning legalizer and sliding‑window approaches, are within 0.1% of optimal on most cases, while other density‑guided and greedy methods can be significantly worse. The authors release the code, optimal values, and dual certificates for these benchmarks.

arXiv Machine Learning
Nov 5

Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes

The paper introduces Adaptive Multi Mode (AMM), a budget‑aware router that selects among several optimization engines—quasi‑Newton, trust‑region, coordinate, multistart, and evolution‑strategy—based on online probes of the problem landscape. Each probe evaluates features such as curvature, plateaus, separability, kinks, basins, and fractal structure, and is assigned a validity range and cost relative to the budget. In extensive pre‑registered tests on the bbob benchmark, AMM achieved the highest target share in 382 of 600 function‑dimension‑budget cells, outperforming up to seven competitors and maintaining strong performance across transformations and constraints.

By Benjamin Jacob Bodner
arXiv AI
Oct 19

Hard Instances on Demand

The paper presents a method for generating hard problem instances by treating instance creation as an optimization problem, using solver runtime as the objective. Leveraging the Nevergrad platform, the authors generate challenging instances for four NP‑hard problems—satisfiability, traveling salesperson, Hamiltonian cycle, and non‑permutation flow‑shop scheduling—that outperform random draws and rival curated benchmark sets. The approach requires only a solver, an instance encoder, and a compute budget, and it can uncover structural insights such as phase‑transition behavior in SAT.

By Jamie Fravel, Martin Kouteck\'y, Pavlo Tsitsei
arXiv Computation and Language
Sep 25

Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters

The study re‑examines a reported advantage of a routed ternary (1.58‑bit) language model over a full‑precision transformer at 60K parameters. By running controlled experiments with multiple seeds and a fixed training recipe, the authors find that the apparent benefit largely stems from the choice of baseline model shape rather than the ternary architecture itself. While the routed model does outperform other shapes at a larger 130M‑byte budget, its advantage diminishes when a plain gated diagonal‑SSM block is used, and the ternary penalty varies with architecture and quantization details.

By Gautam Veldanda
Hugging Face Trending Papers
Sep 8

Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training

The paper investigates how per-domain data composition during the mid‑training phase (between pre‑training and alignment) affects model performance. Experiments with Qwen3‑8B‑Base across five KOR‑Bench domains show that a moderate coverage band (10%‑40%) yields the best performance for each domain, and that alignment passes cannot fully close the gaps created by suboptimal mid‑training allocations. Additionally, zero coverage during mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.

arXiv AI
Sep 10

Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training

The study investigates how the composition of data during the mid‑training phase of language models affects performance across multiple domains. Experiments with Qwen3‑8B‑Base on five distinct KOR‑Bench domains show that moderate coverage (10%‑40%) yields the best per‑domain results, and that alignment passes cannot fully close the performance gaps created by mid‑training data choices. Additionally, zero coverage in mid‑training severely degrades accuracy, while a carefully tuned allocation can provide the largest overall pipeline improvement.

By Yunpeng Xu, Kun Zheng