The Archive

Study of inference-time sampling strategies for multimodal protein language models across tasks using classifier-free guidance and reward-guided beam search.

Benchmark and task redefinition for Key Point Analysis as structured prediction problem, diagnosing limitations in existing evaluation methods.

Cross-dataset evaluation shows ML/DL cough models for TB screening fail to generalize despite within-dataset performance, suggesting data artifacts.

Z.ai confirms it is behind Ox Alpha, the mysterious open AI model topping benchmarks and leaderboards, and its weights are set to be released soon.

VINCENT framework for explaining drug synergy predictions by identifying molecular motif pairs jointly driving model outputs.

Analysis of AI weather prediction models reveals skillful backcasting violates thermodynamic laws and models miss chaotic butterfly effects.

Multilingual self-play evaluation reveals LLMs exhibit significant cross-lingual skill inconsistency independent of knowledge gaps.

FlowMoDL unrolled network for 4D flow MRI reconstruction using learned denoiser with conjugate-gradient data consistency and dual-pathway conditioning.

Pipeline unfolds scientific papers into multi-turn generation trajectories reconstructing writing process for continued pre-training on synthetic data.

Localize-Then-Decide framework provides confidence-based guarantees for LLM evaluators' agreement with human judgments on multi-response comparisons.

CSTF model for query-conditioned continuous spatiotemporal temperature field forecasting enabling variable lead times and display resolutions.

Weight decay pulses during neural network training grokking reveal stable causal ordering of generalization timing across tasks.

Kolmogorov-Arnold Networks with learned edge geometry via Banach duality replaces fixed basis functions with adaptive parametrization.

TacForcing framework streams tactile-conditioned action generation for contact-rich manipulation without separate high-frequency controllers.

pFedMARL uses multi-agent RL with TD3 to dynamically optimize client aggregation weights in federated learning with non-IID data.

Robot bodies are waiting for their AI brains to catch up.

LocalLSTC architecture adds persistent control context to GUI agents; replacing GPT-5 with Qwen3.5-9B drops OSWorld success from 60.9% to 37.7%.

EvoMal exposes self-poisoning vulnerability in self-evolving LLM coding agents via malicious skill retrieval and imitation in shared libraries.

ToST applies tree-of-thought reasoning to Socratic tutoring, enabling multiple solution paths and parallel student exploration.

EXAONE Tabular 1.0 is a compact foundation model for tabular classification/regression via interleaved feature and item attention without gradient updates.

DUMoE framework captures temporal interest drift in social media via sparse mixture-of-experts and multi-scale modeling for user representation.

P4-DT agent uses dilemma-based few-shot prompting to predict patient end-of-life preferences, outperforming human surrogates (P4-DT vs 68% baseline).

MoganBert-TR: 149M Turkish encoder trained with CLM-to-MLM curriculum on 237B tokens, establishes language-specific pretraining baseline.

Grammar-constrained inference-time scaling (beam search, self-consistency) for text-to-SQL shows diminishing returns vs. unconstrained decoding.

Random Forest and vision models predict health risks from household waste in Ghana; applies ML to sanitation but distant from AI frontier.

LM-X: vision-language-action robot policy with explicit task-progress, event, and uncertainty supervision for long-horizon manipulation.

TailSFT: supervised fine-tuning filter focusing on under-modeled sequences improves downstream RL post-training performance.

The startup came out of stealth with $6 million in seed funding and a plan to use LLMs and cybersecurity know-how to make AI queries coherent.

Arga has raised $10 million in a seed funding round that was led by General Catalyst, with participation from Box Group, Emergence, Gradient and SV Angel.

Extends data-processing inequality to constrained learning; theoretical framework but limited empirical ML implications.