arXiv:2605.11875v1 Announce Type: cross Abstract: Deep learning-based AMC methods have achieved remarkable performance, but their practical deployment remains constrained by the high cost of labeled data. Although self-supervised learning (SSL) reduces the reliance on labels, existing SSL-based AMC methods often rely on task-agnostic pretext objectives misaligned with modulation classification, leading to representations entangled with nuisance […]
DiffScore: Text Evaluation Beyond Autoregressive Likelihood
arXiv:2605.11601v1 Announce Type: cross Abstract: Autoregressive language models are widely used for text evaluation, however, their left-to-right factorization introduces positional bias, i.e., early tokens are scored with only leftward context, conflating architectural asymmetry with true text quality. We propose masked reconstruction as an alternative paradigm, where every token is scored using full bidirectional context. We […]
The Same Problem by Different Names: Unifying Regression Dilution and Regression to the Mean
arXiv:2605.11197v1 Announce Type: new Abstract: Regression to the Mean and Regression Dilution are often viewed as unrelated issues in the clinical and ecological literatures. In reality, they are different names for the same problem: measurement error in an independent variable that biases the perceived relationship between two factors. This study unifies these traditions by comparing […]
Overtrained, Not Misaligned
arXiv:2605.12199v1 Announce Type: cross Abstract: Emergent misalignment (EM), where fine-tuning on a narrow task (like insecure code) causes broad misalignment across unrelated domains, was first demonstrated by Betley et al. (2025). We conduct the most comprehensive EM study to date, reproducing the original GPT-4o finding and expanding to 12 open-source models across 4 families (Llama, […]
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
arXiv:2605.10989v1 Announce Type: cross Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevailing methods including the Straight-Through Estimator (STE) and its improved variants, rely on hand-crafted designs that suffer from gradient mismatch problem and information loss induced by fixed-range gradient clipping. […]
Don’t Look at the Numbers: Visual Anchoring Bias and Layer-wise Representation in VLMs
arXiv:2605.11218v1 Announce Type: new Abstract: Embedded numeric anchors on images systematically bias Vision-Language Model quality judgments across six VLMs from five architectural families (ANOVA eta^2 = 0.18-0.77, all p < 0.001). Anchor effects are 2.5x larger than severe image quality degradation, confirming bias is not reducible to visual changes. Layer-wise probing reveals consistent dissociation: layers […]
DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
arXiv:2605.11005v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) architectures enable trillion-parameter LLMs with sparsely activated experts. Expert parallelism (EP) is a widely adopted MoE training strategy, but it suffers from severe all-to-all communication bottlenecks, which is exaggerated by the limited inter-node network bandwidth as the growing model size requires distributing experts across GPU nodes. Prior work […]
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
arXiv:2605.12411v1 Announce Type: cross Abstract: AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart’s LLM, prompts, control logic, and rule-based fallbacks are hidden, while each decision can have monetary consequences. We ask whether […]
Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
arXiv:2605.11019v1 Announce Type: cross Abstract: Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate reward functions, which renders high-quality samples extremely sparse in the exploration space and creates a sampling bottleneck for the prior policy. Inspired by […]
Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows
arXiv:2605.11221v1 Announce Type: new Abstract: Predictive models in biomedicine depend on structured assay data locked in the text, tables, and supplements of primary publications. This bottleneck is especially acute in targeted protein degradation (TPD), where each assay record must combine compound identity, degradation target, recruiter, assay context, and endpoint values reported across sections, tables, and […]
The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck
arXiv:2605.11039v1 Announce Type: cross Abstract: Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity of an entire tool invocation, forcing a brittle choice in mixed-trust workflows: allow external content to influence a call and risk hijacked destinations or […]
Probing RLVR training instability through the lens of objective-level hacking
arXiv:2602.01103v2 Announce Type: replace Abstract: Prolonged reinforcement learning with verifiable rewards (RLVR) has been shown to drive continuous improvements in the reasoning capabilities of large language models, but the training is often prone to instabilities, especially in Mixture-of-Experts (MoE) architectures. Training instability severely undermines model capability improvement, yet its underlying causes and mechanisms remain poorly […]