arXiv:2605.04097v1 Announce Type: new Abstract: Despite remarkable advances, today’s AI systems remain narrow in scope, falling short of the flexible, adaptive, and multisensory intelligence that characterizes human capabilities. This gap has fueled longstanding debates about whether AI might one day achieve human-like generality or even consciousness, and whether theories of consciousness can inspire new architectures […]
Learning reveals invisible structure in low-rank RNNs
arXiv:2605.04115v1 Announce Type: cross Abstract: Learning in neural systems arises from synaptic changes that reshape the representations underlying behavior. While low-rank recurrent neural networks (RNNs) have emerged as a powerful framework for linking connectivity to function, a theoretical understanding of their learning process remains elusive. Here, we extend the low-rank framework from activity to learning […]
DPD-Cancer: Explainable Graph-Based Deep Learning for Small Molecule Anti-Cancer Activity Prediction
arXiv:2603.26114v2 Announce Type: replace-cross Abstract: DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule anti-cancer activity across the NCI-60 panel, trained and evaluated under a strict chemistry-aware data-partitioning scheme. On the hold-out test set, the classifier achieved an Area Under the Receiver Operating Characteristic […]
Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes
arXiv:2605.04797v1 Announce Type: cross Abstract: Deepfakes are increasingly realistic and easy to produce, raising concerns about the reliability of human judgments in misinformation settings. We study audiovisual deepfake detection by measuring how consistently crowd workers distinguish authentic from manipulated videos and, when they flag a video as manipulated, how accurately they identify the manipulation type […]
Control of genes by self-organizing multicellular interaction networks
arXiv:2603.26530v2 Announce Type: replace Abstract: Multicellular self-organization drives development in biological organisms, yet a comprehensive theory is lacking as basic properties of cells can complicate common approaches. Framing such properties by dynamic graphs led to new theoretical propositions for multicellular self-organization in Escherichia coli. Here, corresponding ideas are developed from biologically-general first principles. The resulting […]
An explainable hypothesis-driven approach to Drug-Induced Liver Injury with HADES
arXiv:2605.02669v2 Announce Type: replace Abstract: Drug-induced liver injury (DILI) remains a leading cause of late-stage clinical trial attrition. However, existing computational predictors primarily rely on binary classification, a framing that limits generalization and yields no mechanistic insight to guide translational decisions. We argue that DILI prediction is better posed as an explainable hypothesis-generation problem. To […]
What Matters in Practical Learned Image Compression
arXiv:2605.05148v1 Announce Type: cross Abstract: One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed. In this work, we aim to close […]
Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction
arXiv:2508.19035v2 Announce Type: replace Abstract: Existing tasks fall short in evaluating reasoning ability of Large Language Models (LLMs) in an interactive, unknown environment. This deficiency leads to the isolated assessment of deductive, inductive, and abductive reasoning, neglecting the integrated reasoning process that is indispensable for human-like discovery learning. We introduce a novel evaluation paradigm, textitblack-box […]
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Separation
arXiv:2604.27201v2 Announce Type: replace-cross Abstract: Hybrid-thinking language models expose explicit think and no-think modes, but current designs do not separate them cleanly. Even in no-think mode, models often emit long and self-reflective responses, causing reasoning leakage. Existing work reduces this issue through better data curation and multi-stage training, yet leakage remains because both modes are […]
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
arXiv:2605.05040v1 Announce Type: cross Abstract: On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the same model serves as both teacher and student under different prompt contexts. Yet, existing self-distillation methods largely reduce learning […]
SWE Context Bench: A Benchmark for Context Learning in Coding
arXiv:2602.08316v3 Announce Type: replace-cross Abstract: Large language models are increasingly used as coding agents for software engineering tasks. Current benchmarks mainly evaluate whether the agent can correctly solve the request or fix the bugs. They largely treat tasks as independent and do not assess whether agents can reuse previous experience across related problems. As a […]
Emergent Hierarchical Structure in Large Language Models: An Information-Theoretic Framework for Multi-Scale Representation
arXiv:2505.18244v3 Announce Type: replace-cross Abstract: Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale, but emphhow architecture shapes information compression. Analyzing eight Transformer models (7B–70B parameters) from the Llama and Qwen families, we show that every model spontaneously develops discrete functional […]