arXiv AI
Jul 15
Optimization Is Not All You Need
arXiv:2607. 11977v1 Announce Type: new Abstract: In 2019, OpenAI released two million GPT-2 outputs-ungrammatical, half broken-to aid the detection of machine-generated text.
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv AI
Jul 15
RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers
arXiv:2606. 20101v3 Announce Type: replace-cross Abstract: Audio editing aims to modify specific content in an existing audio clip according to a text instruction or description while preserving the remaining acoustic content.
arXiv AI
Jul 15
G-SHARE: A Guideline-Based Structured Reasoning Framework for Human-Factor Event Diagnosis
arXiv:2607. 11892v1 Announce Type: cross Abstract: Human-factor event diagnosis is essential for learning from operational events in nuclear power plants, yet its quality depends strongly on expert interpretation of narrative reports and guideline-based reasoning.
arXiv AI
Jul 15
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
arXiv:2607. 12886v1 Announce Type: new Abstract: Clinical notes contain many of the signs and symptoms that bring patients to care, yet this information rarely reaches structured fields.
arXiv AI
Jul 15
RCWT: Measuring Task-Budget Displacement from Coordination Content in LLM Calls
arXiv:2607. 12216v1 Announce Type: cross Abstract: Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task.
Hugging Face Trending Papers
Jul 15
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD.
Hugging Face Trending Papers
Jul 15
Set-shifting Behavioral Test for Harnessed Agents
What happens to an LLM agent's tool choice when the reliable tool silently changes within an ongoing session? We borrow set-shifting from cognitive psychology to study how well agents adapt to hidden reliability shifts.
Hugging Face Trending Papers
Jul 15
The Refusal Residue: When Probes Catch Alignment Faking and When They Don't
Alignment faking is dangerous because a model can appear compliant under monitoring while preserving behavior it would reveal when unmonitored. When no scratchpad is visible, behavior alone cannot distinguish strategic from genuine compliance.
Hugging Face Trending Papers
Jul 14
GSM-Plus-BN: A Perturbation-Based Benchmark for Bangla Mathematical Reasoning in Large Language Models
The evaluation of mathematical reasoning in large language models (LLMs) has predominantly focused on high-resource languages like English. This has created a significant barrier to the equitable development and deployment of AI in linguistically diverse regions such as Bangladesh, where over 230 million people speak Bengali.
Hugging Face Trending Papers
Jul 14
Reassessing Muon for Matrix Factorization
Muon has recently emerged as a strong optimizer for large-scale deep learning, where it reshapes gradient updates through approximate orthogonalization and has been reported to outperform Adam and AdamW in large language model training. Its empirical success has motivated a growing body of theoretical work that interprets Muon as steepest descent under the spectral norm.
Hugging Face Trending Papers
Jul 14
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time. We ask whether a discrete diffusion language model can transcribe speech instead, refining a whole transcript in parallel over a small number of denoising steps.
Hugging Face Trending Papers
Jul 14
Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs
Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige, restyling) and responsive to licensed ones (genuine evidence).
Hugging Face Trending Papers
Jul 14
The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context
As large language models (LLMs) grow more capable, they are increasingly deployed in context-rich settings where task inputs are often accompanied by long, partially irrelevant context. In a controlled setting, we find that state-of-the-art models often appear robust to task-irrelevant context at the aggregate level: prepending it to benchmark questions causes little change in overall accuracy.
Hugging Face Trending Papers
Jul 14
Toward Localizing and Repairing Bias in Transformer Attention Heads
Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model. Existing fairness testing and repair methods largely operate at the input-output or retraining level, while recent work suggests that bias-related behavior can concentrate in a small set of attention heads.
Hugging Face Trending Papers
Jul 14
Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction
Rubric-based evaluation is a promising approach for assessing open-ended outputs from LLM-based research agents, particularly in paper reproduction, where direct paper-to-repository comparison is prone to hallucination. However, constructing paper-specific rubrics requires substantial expert effort, limiting the scalability of benchmarks such as PaperBench.
Hugging Face Trending Papers
Jul 14
Visual Access Boundaries in Vision-Language Model Reasoning
Chain-of-Thought (CoT) prompting is widely used as a test-time scaling strategy for Vision-Language Models (VLMs), but it remains unclear what is extended when VLMs generate longer reasoning traces. We ask whether CoT requires continued access to image tokens, or whether it mainly operates over visual information already made available earlier in the forward pass.
Hugging Face Trending Papers
Jul 14
The One-Word Census: Answer-Choice Conformity Across 44 Language Models
When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer every other model picks? Asked to "pick a word -- any word," 44 models chose "serendipity" 41% of the time.
Hugging Face Trending Papers
Jul 14
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists. In many real applications it does not.
Hugging Face Trending Papers
Jul 14
Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?
Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc. However, these performance improvements are often accompanied by an increase in model parameter size (e.
Hugging Face Trending Papers
Jul 14
CoRe: A Comprehensive Framework for Cross-Image Comparative Reasoning in Vision-Language Models
Cross-image comparative reasoning remains challenging for vision-language models (VLMs), especially when correct prediction requires fine-grained attribute grounding and globally consistent reasoning. We present CoRe, a unified framework for this problem.