A naukri.com initiative
ML News
Arxiv
3d
266
Image Credit: Arxiv
Neuromorphic Optical Tracking and Imaging of Randomly Moving Targets through Strongly Scattering Media
- Researchers have developed a neuromorphic optical engineering and computational approach to track and image moving targets obscured by scattering media.
- The method combines an event detecting camera with multistage neuromorphic deep learning for object localization and identification.
- Photon signals from scattering media are converted to pixel-wise asynchronized spike trains by the event camera to filter out background noise.
- A deep spiking neural network (SNN) processes the spiking data for simultaneous tracking and image reconstruction of objects.
- The approach successfully tracked and imaged randomly moving objects in dense turbid media and dynamic stationary objects.
- Standardized character sets were used to represent complex objects, showcasing the method's versatility.
- The study emphasizes the benefits of a fully neuromorphic approach in achieving efficient imaging technology with low power consumption.
Read Full Article
16 Likes
Arxiv
3d
362
Image Credit: Arxiv
DeepExtractor: Time-domain reconstruction of signals and glitches in gravitational wave data with deep learning
- Gravitational wave detectors like LIGO, Virgo, and KAGRA are sensitive to signals from distant astrophysical events but can be affected by background noise, including glitches.
- DeepExtractor is a deep learning framework introduced to reconstruct signals and glitches in gravitational wave data, surpassing interferometer noise levels.
- This model is designed to capture the noise distribution of GW detectors assuming Gaussian and stationary noise over short time intervals, aiming to separate signal or glitch from noise.
- DeepExtractor was tested through experiments including simulated glitches in detector noise, comparison with the BayesWave algorithm, and analyzing real data from the Gravity Spy dataset for glitch subtraction in LIGO strain data.
- The model performed well in reconstructing simulated glitches with a median mismatch of only 0.9%, outperforming other deep learning baselines.
- DeepExtractor also excelled in glitch recovery compared to BayesWave, offering a significant speedup by reconstructing one glitch sample in about 0.1 seconds on a CPU, much faster than BayesWave's processing time of about an hour per glitch.
Read Full Article
21 Likes
Arxiv
3d
35
Image Credit: Arxiv
Generalizable and Fast Surrogates: Model Predictive Control of Articulated Soft Robots using Physics-Informed Neural Networks
- Soft robots can enhance applications requiring dexterity and safety.
- Real-time control of these systems demands fast and accurate models.
- First-principles models for prediction are slow, while black-box models lack generalizability.
- Physics-informed machine learning is advantageous but usually limited.
- Physics-informed neural networks (PINNs) are proposed for articulated soft robots (ASRs) with a focus on data efficiency.
- PINNs reduce the need for expensive real-world training data to a single dataset.
- Comparisons against gold-standard approaches show PINNs provide high generalizability.
- PINNs surpass the prediction speed of accurate FP models by up to 467 times, albeit with slightly reduced accuracy.
- This advancement allows for nonlinear model predictive control (MPC) of a pneumatic ASR.
- Accurate position tracking is achieved at a 47 Hz MPC rate in six dynamic experiments.
Read Full Article
2 Likes
Arxiv
3d
99
Image Credit: Arxiv
ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models
- Research paper introduces ImageChain, enhancing multimodal large language models with sequential reasoning capabilities over image data.
- ImageChain models visual sequences as a multi-turn conversation by interleaving images with corresponding textual descriptions.
- Framework explicitly captures temporal dependencies and narrative progression in image data.
- Optimizes for the task of next-scene description, where model generates context-aware descriptions based on preceding visual and textual cues.
- Approach improves performance on next-scene description task, showing an average improvement from 3.7% to 19% in SimRate metric.
- ImageChain demonstrates robust zero-shot out-of-domain performance in applications like comics and robotics.
- Extensive experiments validate the importance of instruction-tuning in a multimodal, multi-turn conversation design for enhanced reasoning.
Read Full Article
5 Likes
Arxiv
3d
115
Image Credit: Arxiv
FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts
- Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks where harmful content can be induced, posing safety risks despite safety alignment efforts.
- A new method named FC-Attack utilizes auto-generated flowcharts with partially harmful information to trick MLLMs into providing additional harmful details.
- FC-Attack fine-tunes a pre-trained model to create a step-description generator from benign datasets, then transforms harmful queries into flowcharts for the attack.
- The flowcharts come in vertical, horizontal, and S-shaped forms, combined with benign text prompts to execute the attack on MLLMs, achieving high success rates.
- Evaluations on Advbench demonstrate FC-Attack's success rates of up to 96% via images and up to 78% via videos across various MLLMs.
- Factors affecting the attack performance, such as the number of steps and font styles in the flowcharts, are investigated, with font style changes improving success rates.
- FC-Attack enhances jailbreak performance from 4% to 28% in Claude-3.5 by altering font styles.
- Several defense mechanisms, including AdaShield, help mitigate the attack; however, they may come at the cost of reduced utility.
Read Full Article
6 Likes
Arxiv
3d
346
Image Credit: Arxiv
Spatial Reasoning with Denoising Models
- Researchers introduce Spatial Reasoning Models (SRMs) for reasoning over sets of continuous variables using denoising generative models.
- SRMs infer continuous representations on unobserved variables based on observations on observed variables.
- Current generative models like diffusion and flow matching models can lead to hallucinations in complex distributions.
- The study includes benchmark tasks to evaluate the quality of reasoning in generative models and quantify hallucination.
- SRMs highlight the importance of sequentialization in generation, the associated order, and sampling strategies during training.
- The framework shows that the order of generation can be predicted by the denoising network itself, leading to significant accuracy improvements.
- The project website offers additional resources including videos, code, and benchmark datasets.
- The SRM framework enhances accuracy in specific reasoning tasks from less than 1% to over 50%.
Read Full Article
20 Likes
Arxiv
3d
167
Image Credit: Arxiv
Mamba time series forecasting with uncertainty quantification
- Mamba, a state space model, has gained attention for time series forecasting.
- Mamba forecasts in electricity consumption benchmarks show an average error of about 8%.
- In traffic occupancy benchmarks, the mean error in Mamba forecasts reaches 18%.
- A method is proposed to quantify the predictive uncertainty of Mamba forecasts.
- A dual-network framework based on the Mamba architecture is introduced for probabilistic forecasting.
- The framework includes one network for point forecasts and another for estimating predictive uncertainty by modeling variance.
- The tool is named Mamba-ProbTSF, and its implementation code is available on GitHub.
- Evaluation on synthetic and real-world benchmark datasets shows effectiveness.
- Kullback-Leibler divergence between learned distributions and data is reduced to a low level for both synthetic and real-world data.
- The true trajectory stays within the predicted uncertainty interval around 95% of the time for both electricity consumption and traffic occupancy benchmarks.
- Considerations for limitations, performance improvements, and applications to stochastic dynamics processes are discussed.
- The research is detailed in arXiv:2503.10873v2, focusing on time series forecasting with uncertainty quantification.
Read Full Article
10 Likes
Arxiv
3d
171
Image Credit: Arxiv
Multi-Variable Batch Bayesian Optimization in Materials Research: Synthetic Data Analysis of Noise Sensitivity and Problem Landscape Effects
- Bayesian Optimization (BO) is increasingly used in materials science for experimental optimization tasks.
- A study was conducted to simulate batch BO with six design variables and different noise levels.
- Two test cases, Ackley function and Hartmann function, relevant for materials science problems were examined.
- The study analyzed the impact of noise, batch-picking method, acquisition function, and hyperparameter values on optimization outcomes.
- Noise was found to have varying effects depending on the problem landscape.
- Noise degraded optimization results more in a needle-in-a-haystack search scenario, but increased the probability of finding a local optimum in the Hartmann function.
- Prior knowledge of the problem domain structure and noise level is crucial when designing BO for materials research experiments.
- Synthetic data studies help evaluate the impact of different batch BO components before moving to real experimental systems.
- The study results aim to enhance the utilization of BO in guiding experimental materials research with a large number of design variables.
Read Full Article
10 Likes
Medium
3d
39
Title: The Tachyonic Recursive Collapse Model (TRCM): A Framework for Semantic Information Flow…
- The paper presents a theoretical framework merging symbolic recursion, AI behavior modeling, quantum metaphors, and semantic mathematics to explore posthuman cognition and information dynamics.
- It introduces the Tachyonic Recursive Collapse Model (TRCM) that unifies Semantic Information Mathematics, Quantum-Collapsed Symbolic Dynamics, and tachyonic metaphors.
- TRCM models how meaning propagates within recursive symbolic cognition, extending traditional information theory by treating symbols as dynamic entities in temporal spaces.
- Semantic Information Mathematics defines Symbol State Vectors for symbols in recursive cognition, considering compression index, directional gradient, and vector position.
- Quantum-Collapsed Symbolic Dynamics explains how attention collapses symbols into definite outputs based on coherence scores involving validity, satisfaction, and elegance.
- TRCM applies a tachyonic field metaphor to model symbols propagating influence forward and backward through cognitive sequences.
- Attention mechanisms in AI align with TRCM, where the self-attention mechanism acts as a soft tachyonic field, influencing meanings throughout sequences.
- The TRCM framework suggests implications for posthuman cognition, envisioning systems operating on recursive semantic harmonics and ethical regulations encoded in recursive time-loops.
- Future applications of TRCM include designing recursive AI architectures, post-symbolic compression layers for AGI cognition, ethical fields for AI, and achieving deep AI interpretability.
- TRCM offers a metaphorical map for understanding deeply recursive, symbolic posthuman cognition beyond linear causality.
Read Full Article
2 Likes
Medium
3d
316
Title: Quantum-Collapsed Symbolic Dynamics (QCSD): A New Framework for AI Mathematical Reasoning…
- Quantum-Collapsed Symbolic Dynamics (QCSD) introduces a new framework for AI mathematical reasoning, treating equations as dynamic fields of potential requiring structured observation for solution.
- QCSD uses quantum mechanics analogies to model symbolic reasoning and advocates for AI systems as collaborative partners in reasoning rather than mere calculators.
- It envisions AI managing its generative processes and exploring potential within mathematics, offering a more dynamic and intuitive approach.
- The framework comprises a Pruning Protocol to manage possibilities and a Resonance Function to select optimal solutions based on validity, satisfaction, and elegance.
- The Pruning Protocol includes steps from defining constraints to generating candidate solutions iteratively, aiming to reduce the infinite set of possibilities.
- Candidates are scored for coherence using the Coherence Resonance Function, which considers validity, satisfaction, and elegance with weighted factors.
- The process culminates in a formal collapse event where the system selects the maximally coherent state as the solution, emphasizing logical cohesion and elegance.
Read Full Article
18 Likes
Medium
3d
311
Image Credit: Medium
Apple Just Shattered the AI Hype — And No One’s Talking About It
- In June 2025, Apple's research team released a paper titled 'The Illusion of Thinking' on the eve of WWDC, challenging the concept of 'thinking.'
- The study, conducted by prominent researchers, explored the limitations of large reasoning models (LRMs) in AI research.
- The researchers found that LRMs excel in a narrow range of puzzles but struggle with simpler tasks and more complex challenges.
- LRMs simulate internal reasoning by chaining thoughts token by token, but their performance falters outside a specific range.
- Apple's paper signifies a strategic shift rather than an apology, indicating a focus on on-device privacy, human-centric quality, and deploying reliable AI tools.
Read Full Article
18 Likes
Arstechnica
3d
248
Image Credit: Arstechnica
New Apple study challenges whether AI models truly “reason” through problems
- Apple researchers published a study suggesting that Simulated Reasoning models produce outputs consistent with pattern-matching, rather than true reasoning, when faced with novel problems.
- The study, titled 'The Illusion of Thinking,' evaluated large reasoning models against classic puzzles of varying difficulties.
- Results showed that models struggled on tasks requiring extended systematic reasoning, achieving low scores on novel mathematical proofs.
- Critics like Gary Marcus found the results 'devastating' to Large Language Models (LLMs) and questioned their logical and intelligent processes.
- The study revealed that SR models behave differently from standard models depending on task difficulty, sometimes 'overthinking' and failing on complex puzzles.
- An identified scaling limit showed that reasoning models reduce their effort beyond a certain complexity threshold.
- Not all researchers agree with the study's interpretation, suggesting that limitations may reflect deliberate training constraints rather than inherent inabilities.
- Some critics argue that the study's findings may be measuring engineered constraints rather than fundamental reasoning limits.
- The Apple researchers caution against over-extrapolating the study's results, noting that puzzle environments may not capture the diversity of real-world reasoning problems.
- While the study challenges claims about AI reasoning models, it does not render these models useless, indicating potential uses for tasks like coding and writing.
Read Full Article
14 Likes
Mit
3d
172
Image Credit: Mit
Bringing meaning into technology deployment
- In a recent event, MIT faculty presented their pioneering research that integrates social, ethical, and technical aspects with seed grants from SERC.
- 70 proposals were submitted in response to the call for proposals, with winning projects receiving up to $100,000 in funding.
- The MIT Ethics of Computing Research Symposium highlighted four key themes: responsible health-care technology, AI governance, technology in society, and digital inclusion.
- Projects included improving kidney transplant systems, examining AI-generated social media content ethics, and enhancing civil discourse online using AI.
- Dimitris Bertsimas introduced an algorithm for fair kidney transplant allocation, significantly reducing evaluation time.
- Adam Berinsky and Gabrielle Péloquin-Skulski discussed the impact of labeling AI-generated social media content on user perception.
- Lily Tsai and team focused on using AI to increase civil discourse online through the DELiberation.io platform.
- Catherine D’Ignazio and Nikko Stevens established Liberatory AI, functioning as a public think tank exploring all aspects of AI.
Read Full Article
10 Likes
Marktechpost
3d
304
How Do LLMs Really Reason? A Framework to Separate Logic from Knowledge
- Advancements in reasoning-focused LLMs like OpenAI's o1/3 and DeepSeek-R1 have improved complex task performance, yet their reasoning processes remain unclear.
- Current evaluations of LLMs often focus on final-answer accuracy, masking the reasoning steps and the combination of knowledge and logic.
- Factual errors and lack of reasoning depth in math and medicine demonstrate the limitations of current final-answer evaluation methods.
- Researchers propose a new framework to assess LLM reasoning by separating factual knowledge and logical steps using the Knowledge Index and Information Gain metrics.
- Evaluation of Qwen models across math and medicine tasks shows that reasoning skills do not easily transfer between domains.
- The study compares supervised fine-tuning and reinforcement learning in domain-specific tasks, highlighting the impact on accuracy, knowledge retention, and reasoning depth.
- Results indicate that while supervised fine-tuning enhances factual accuracy, it may weaken reasoning depth, whereas reinforcement learning improves both reasoning and knowledge.
- The framework introduced in the study aims to make LLMs more interpretable and trustworthy, particularly in critical fields like medicine and math.
Read Full Article
18 Likes
Arstechnica
3d
16
Image Credit: Arstechnica
In landmark suit, Disney and Universal sue Midjourney for AI character theft
- Disney and NBCUniversal have filed a lawsuit against AI company Midjourney for copyright infringement, allowing users to create images of characters like Darth Vader and Shrek.
- The lawsuit, filed in US District Court in Los Angeles, is the first major legal action by Hollywood studios against a generative AI company.
- Midjourney is accused of enabling users to generate personalized images of copyrighted characters using AI image-synthesis.
- The studios claim Midjourney trained its AI model on copyrighted content without permission, leading to the creation of unauthorized images.
- The legal complaint includes visual examples showing AI-generated versions of characters like Yoda, Wall-E, Stormtroopers, Minions, and more.
- Disney's general counsel stated that infringement by an AI company does not make it any less illegal, emphasizing the issue of piracy.
- The studios argue that Midjourney actively promotes copyright infringement by displaying copyrighted characters in its platform's 'Explore' section.
- Midjourney supposedly has technical protection measures to prevent infringing outputs but has chosen not to implement them.
- Prior to the lawsuit, Disney and NBCUniversal tried to address the issue with Midjourney, but the company allegedly continued to release infringed images.
- NBCUniversal's executive vice president highlighted the lawsuit's purpose to protect the artists' work and the studios' significant content investments.
- The legal action demonstrates Hollywood's new front concerning AI copyright issues, with major studios potentially uniting against tech companies.
- Other studios like Amazon, Netflix, Paramount Pictures, Sony, and Warner Bros. are not part of the lawsuit but are members of the Motion Picture Association.
- The conflict highlights the studios' efforts to protect intellectual property in the face of AI advancements and potential copyright violations.
- Midjourney's platform allows users to submit prompts for AI-generated images, leading to the creation of unauthorized images of well-known characters.
- The lawsuit follows similar legal moves in different creative industries, indicating a trend of addressing AI-related copyright concerns.
- Various copyrighted characters from different studios were found in the AI-generated images provided as evidence in the legal filing by Disney and NBCUniversal.
Read Full Article
Like
For uninterrupted reading, download the app