Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models
arXiv:2610.18990v1 Announce Type: new
Abstract: Low-Rank Adaptation (LoRA) has made diffusion model personalization affordable and widely shareable, but it also creates moderation risks when harmful or problematic content is not faithfully disclosed. Hence, it is desired to develop a mechanism that...
The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery
arXiv:2610.18933v1 Announce Type: new
Abstract: Modern coding agents are fundamentally reshaping the role of human input for computational research: they write code, launch in silico experiments, analyze their results, and autonomously operate with ever-increasing time horizons. Despite these devel...
Lotus: Learning to Understand Time-series by Learning to Forecast
arXiv:2610.18877v1 Announce Type: new
Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervision encourages linguistic representations, it does not explicitly require them to preserve information ...
Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data
arXiv:2610.18878v1 Announce Type: new
Abstract: Post-training reasoning LLMs often requires making a tradeoff between costly supervision and compute inefficiency: supervised finetuning typically requires reasoning traces, which is data inefficient since in many applications one only has prompt-answ...
Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening
arXiv:2610.18880v1 Announce Type: new
Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A difficult case arises when both genes in a test pair were seen individually during training, but thei...
Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders
arXiv:2610.18879v1 Announce Type: new
Abstract: Protein function annotation operates over an expanding label space, making class-incremental learning (CIL) a natural framework for incorporating newly discovered functions without full retraining. Yet existing CIL methods have been developed largely ...
Multimodal agents commonly generate freeform reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action generation while incurring substantial inference cost. To address this challenge, we introduce Selection...
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
arXiv:2610.14146v1 Announce Type: new
Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary check. We present Long-Horizon-Terminal-Bench 2.0 (LHTB 2.0), an extension...
arXiv:2610.14136v1 Announce Type: new
Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed from its own imperfect predictions from the earlier...
ClawLoop: Self-Improving Agents via Harness-Native Training Loop
arXiv:2610.14118v1 Announce Type: new
Abstract: The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post...
arXiv:2610.14115v1 Announce Type: new
Abstract: Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model develo...
Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence
arXiv:2610.14005v1 Announce Type: new
Abstract: Under the accelerated pace of AI development, any benchmark whose difficulty is calibrated with humans or current AI systems becomes circular, or saturates soon. How can we then evaluate machines that may become more capable than the current machines ...
Google DeepMind and Singapore Government announce new AI tool to protect citizens against scams
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
AI can act exactly like a human, but we still don't think it's conscious
A new study reveals that people draw a surprisingly sharp line between human consciousness and artificial intelligence, even when both behave identically. Researchers found that participants considered even the most responsive AI less conscious than the least responsive human. Yet when asked about "...
Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models
Code-switching (CS), the alternation between languages within an utterance, is common in multilingual speech but underrepresented in pretraining corpora. Increasing CS coverage requires finding relevant utterances in large speech collections so that they can be included in training data. One way to ...
The Design Space of Tri-Modal Masked Diffusion Models
Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and finetuning a base unimodal model for bi-modal generation. Diverging from previous approaches, we introduce the first tri-modal Masked Diffusion Models (MDM) pretrained f...
From Prompt to Performance: The Five Stages of Agentic Merchandising
Agentic commerce is no longer just a shopper-side story. The same AI that guides your customers is now reaching into the back office, where merchandisers still configure rules, analyze performance, and replicate campaigns across storefronts by hand.
For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such as high weight decay, and mixing in data from a high-resourc...
Simulating student learning for better AI tutoring
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics.
The post Simulating student learni...
CircuitTree: Composing Circuits into A Syllable Transcriber
arXiv:2610.12520v1 Announce Type: new
Abstract: The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each does an identifiable subtask. We develop a practical method for composing arbitrarily many circuits ...