We study the problem of determining whether a piece of text has been authored by a human or by a large language model (LLM). Existing state of the art logits-based detectors make use of statistics derived from the log-probability of the observed text evaluated using the distribution function of a given source LLM. However, relying solely on log probabilities can be sub-optimal. In response, we introduce AdaDetectGPT -- a novel classifier that adaptively learns a witness function from training data to enhance the performance of logits-based detectors. We provide statistical guarantees on its true positive rate, false positive rate, true negative rate and false negative rate. Extensive numerical studies show AdaDetectGPT nearly uniformly improves the state-of-the-art method in various combination of datasets and LLMs, and the improvement can reach up to 58%. A python implementation of our method is available at https://github.com/Mamba413/AdaDetectGPT.

Abstract--Although existing cross-domain continual learning approaches successfully address many streaming tasks having domain shifts, they call for a fully labeled source domain hindering their feasibility in the privacy constrained environments. This paper goes one step ahead with the problem of source-free cross-domain continual learning where the use of source-domain samples are completely prohibited. We propose the idea of rehearsal-free frequency-aware dynamic prompt collaborations (REFEREE) to cope with the absence of labeled source-domain samples in realm of cross-domain continual learning. REFEREE is built upon a synergy between a source-pre-trained model and a large-scale vision-language model, thus overcoming the problem of sub-optimal generalizations when relying only on a source pre-trained model. The domain shift problem between the source domain and the target domain is handled by a frequency-aware prompting technique encouraging low-frequency components while suppressing high-frequency components. This strategy generates frequency-aware augmented samples, robust against noisy pseudo labels. The noisy pseudo-label problem is further addressed with the uncertainty-aware weighting strategy where the mean and covariance matrix are weighted by prediction uncertainties, thus mitigating the adverse effects of the noisy pseudo label. Besides, the issue of catastrophic forgetting (CF) is overcome by kernel linear discriminant analysis (KLDA) where the backbone network is frozen while the classification is performed using the linear discriminant analysis approach guided by the random kernel method. Our rigorous numerical studies confirm the advantage of our approach where it beats prior arts having access to source domain samples with significant margins. HE goal of continual learning (CL) is to deal with lifelong learning environments where a sequence of non-stationary tasks is observed.

Efficient molecular dynamics (MD) simulation is vital for understanding atomic-scale processes in materials science and biophysics. Traditional density functional theory (DFT) methods are computationally expensive, which limits the feasibility of long-term simulations. We propose a novel approach that formulates MD simulation as a time-series forecasting problem, enabling advanced forecasting models to predict atomic trajectories via displacements rather than absolute positions. We incorporate a physics-informed loss and inference mechanism based on DFT-parametrised pair-wise Morse potential functions that penalize unphysical atomic proximity to enforce physical plausibility. Our method consistently surpasses standard baselines in simulation accuracy across diverse materials. The results highlight the importance of incorporating physics knowledge to enhance the reliability and precision of atomic trajectory forecasting. Remarkably, it enables stable modeling of thousands of MD steps in minutes, offering a scalable alternative to costly DFT simulations.

As a developing country, Fiji is facing rapid urbanisation, which is visible in the massive development projects that include housing, roads, and civil works. In this study, we present machine learning and remote sensing frameworks to compare land use and land cover change from 2013 to 2024 in Nadi, Fiji. The ultimate goal of this study is to provide technical support in land cover/land use modelling and change detection. We used Landsat-8 satellite image for the study region and created our training dataset with labels for supervised machine learning. We used Google Earth Engine and unsupervised machine learning via k-means clustering to generate the land cover map. We used convolutional neural networks to classify the selected regions' land cover types. We present a visualisation of change detection, highlighting urban area changes over time to monitor changes in the map.

Most standard algorithms for prediction with expert advice depend on a parameter called the learning rate. This learning rate needs to be large enough to fit the data well, but small enough to prevent overfitting. For the exponential weights algorithm, a sequence of prior work has established theoretical guarantees for higher and higher data-dependent tunings of the learning rate, which allow for increasingly aggressive learning. But in practice such theoretical tunings often still perform worse (as measured by their regret) than ad hoc tuning with an even higher learning rate. To close the gap between theory and practice we introduce an approach to learn the learning rate. Up to a factor that is at most (poly)logarithmic in the number of experts and the inverse of the learning rate, our method performs as well as if we would know the empirically best learning rate from a large range that includes both conservative small values and values that are much higher than those for which formal guarantees were previously available. Our method employs a grid of learning rates, yet runs in linear time regardless of the size of the grid.

Anguished Diddy clutches his head in his hands in first image from disastrous sentencing that's gone from bad to worse Mystery deepens over Hulk Hogan's death as his widow faces fresh anguish I'm no longer sleeping with my husband - and never will again, says MOLLY RYDDELL. I love him, but counted down the moments until he climaxed. Then I couldn't bear it any more and the truth spilled out... so many women feel the same Map shows where new strain of Covid is exploding in 19 states as sufferers are hit with'razor-blade' symptoms US military poised to seize ports and airfields in Venezuela as Trump strikes a fourth'narco-terrorist' boat Body count from Houston's bayous rises as serial killer whispers grip city and residents are told: 'Be vigilant' Selena Gomez's $1.3B fortune could create risks in Benny Blanco marriage despite his $50M success, experts reveal His daughter was warped into an ultra-woke monster and set fire to his life. Now, GOP state senator Jay Block fights back... and reveals the dark secrets she was desperate to hide Realtor with expensive ex-wife arrested over shocking $11.6m claims about how he was funding Palm Beach lifestyle The'middle-class kinks' saving marriages: Wives reveal the eight buzzy sex trends that revived their lagging libidos - including the fantasy husbands are secretly obsessed with Scientists discover key part of the brain that degrades in Alzheimer's... paving way for breakthrough therapies Lori Loughlin's estranged husband Mossimo Giannulli seen with mystery brunette amid shock split Manchester synagogue terrorist was on bail for alleged rape at the time of his rampage and was'struggling with debt' after'splitting up with his wife and young son' Scientists behind study linking Tylenol to autism accuse Trump of'spreading misinformation' Teresa Giudice thought she was going to'die' during panic attack on Special Forces... after she was called'stupid' NASA has gone dark just hours before humans get the closest look at the mysterious object barreling through our solar system . The interstellar object dubbed 3I/ATLAS will come within 18 million miles of Mars on October 3, its closest flyby of any planet this year.

US military poised to seize ports and airfields in Venezuela as Trump strikes a fourth'narco-terrorist' boat Robert Griffin III involved in'scary' car crash with wife and kids as shocking photos emerge I'm no longer sleeping with my husband - and never will again, says MOLLY RYDDELL. I love him, but counted down the moments until he climaxed. Then I couldn't bear it any more and the truth spilled out... so many women feel the same Body count from Houston's bayous rises as serial killer whispers grip city and residents are told: 'Be vigilant' I was so happy after trying a trendy new cosmetic procedure. But 10 years later I suffered a devastating side effect... the doctor had lied His daughter was warped into an ultra-woke monster and set fire to his life. Now, GOP state senator Jay Block fights back... and reveals the dark secrets she was desperate to hide The'middle-class kinks' saving marriages: Wives reveal the eight buzzy sex trends that revived their lagging libidos - including the fantasy husbands are secretly obsessed with Lori Loughlin's husband Mossimo Giannulli seen with mystery brunette in tiny skirt day after shock split Realtor with expensive ex-wife arrested over shocking $11.6m claims about how he was funding Palm Beach lifestyle Trump dollar coin design released by Treasury... and its inspired by the most iconic political photo of the century Fired CNN host Don Lemon's delivers expletive-filled rant at Megyn Kelly for comments about his husband Shroud of Turin mystery deepens as surgeon spots hidden detail that points to Jesus' resurrection Mystery deepens over Hulk Hogan's death as his widow faces fresh anguish Warning as pasta salad is recalled due to risk of'fatal infections' Multiple'UFOs' caught on camera flying over erupting volcano claimed to be a'wormhole' for aliens A swarm of UFOs was seen flying over an active volcano in Mexico this week, reviving a wild theory that the natural landmark could be an alien portal to space .