arXiv AI
Jun 2
Calibrating Uncertainty for Zero-Shot Adversarial CLIP
arXiv:2512. 12997v2 Announce Type: replace-cross Abstract: CLIP delivers strong zero-shot classification but remains highly vulnerable to adversarial attacks.
Fine-tuning and adaptation
LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv AI
Jun 2
Regime-Adaptive Continual Learning for Portfolio Management
arXiv:2606. 00143v1 Announce Type: cross Abstract: Financial markets are inherently non-stationary, exhibiting frequent regime shifts and structural changes that render traditional Portfolio Management (PM) approaches ineffective.
arXiv AI
Jun 2
Demystifying the Optimal Fair Classifier in Multi-Class Classification
arXiv:2606. 00656v1 Announce Type: cross Abstract: Ensuring fair and equitable treatment across diverse groups, particularly in multi-class classification tasks, poses a significant challenge due to the persistent biases inherent in machine learning models.
arXiv Machine Learning
Jun 2
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
arXiv Machine Learning
Jun 2
PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
arXiv:2606. 00944v1 Announce Type: new Abstract: Applying differential privacy (DP) via DP-SGD to Low-Rank Adaptation (LoRA) is a natural approach for privacy-preserving fine-tuning.
arXiv AI
Jun 2
Short-form Text Rewriting with Phi Silica
arXiv:2606. 00462v1 Announce Type: cross Abstract: Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation.
arXiv AI
Jun 2
Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
arXiv:2606. 00428v1 Announce Type: cross Abstract: Low-rank adapters are usually compared by sweeping a small set of ranks, but the rank also fixes the resolution of the parameter budget.
arXiv Machine Learning
Jun 2
Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
arXiv:2605. 31498v2 Announce Type: replace Abstract: A long standing challenge in computational chemistry and biophysics is efficiently sampling the Boltzmann distribution of molecules.
arXiv AI
Jun 2
MOSS-Audio Technical Report
arXiv:2606. 01802v1 Announce Type: cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning.
arXiv Machine Learning
Jun 2
Reconsidering Positional Supervision in Masked Diffusion Language Model Training
arXiv:2601. 22947v2 Announce Type: replace-cross Abstract: Masked diffusion language models (MDLMs) generate text by unmasking tokens in parallel and have recently emerged as alternatives to autoregressive language models.
arXiv Machine Learning
Jun 2
Context-aware child-directed speech detection from long-form recordings
arXiv:2606. 01134v1 Announce Type: cross Abstract: Automatically distinguishing child-directed speech from adult-directed speech in long-form recordings is key to scalable analyses of children's language environments.
arXiv AI
Jun 2
LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models
arXiv:2606. 01838v1 Announce Type: cross Abstract: Agentic language model systems alternate between two structurally distinct step types: structured tool calls (short, deterministic, low perplexity) and open-ended planning/reasoning steps (long, complex, high perplexity).
arXiv AI
Jun 2
RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents
arXiv:2606. 01552v1 Announce Type: new Abstract: Role-playing agents(RPAs) are widely used to steer large language models(LLMs) toward role-consistent behavior, yet existing benchmarks mainly evaluate surface-level fidelity and offer limited insight into decision making under role-alignment value conflicts.
arXiv AI
Jun 2
SDR: Set-Distance Rewards for Radiology Report Generation
arXiv:2606. 00440v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has rapidly advanced reasoning in vision--language models.
arXiv AI
Jun 2
Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning
arXiv:2605. 27000v2 Announce Type: replace-cross Abstract: Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@$K$ as the canonical metric.
arXiv AI
Jun 2
Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion
arXiv:2606. 00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos.
Hugging Face Trending Papers
Jun 1
Drifting Preference Optimization for One-Step Generative Models
One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators.
Hugging Face Trending Papers
Jun 1
Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
Enabling Vision-Language Models (VLMs) to perform spatial reasoning remains challenging. Existing approaches treat VLMs as passive observers, which is difficult for real-world applications.
Hugging Face Trending Papers
Jun 1
Honey, I Shrunk the Arc de Triomphe!
Metric scale monocular geometry estimation has seen significant progress through large-scale data aggregation, yet current foundation models suffer from a persistent ''scale-collapse'' phenomenon: distant landmarks and vast landscapes are metrically underestimated. We hypothesize that this performance gap stems from a training data bottleneck, where existing metric-scale datasets are hardware-constrained to homogenous vehicle-captured LiDAR or short-range indoor scans, or consist of synthetic data that lacks the semantic complexity of the physical world.
Hugging Face Trending Papers
Jun 1
TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech
Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation in spoken-language transcripts.