Value model-guided search is effective in steering the generation but suffers from scaling flaws: Its superiority diminishes with larger sample sizes, underperforming non-search baselines. This limitation arises from reliability degradation in value models in unseen reasoning paths. To address this, we propose an uncertainty-aware search framework that includes two key components: (1) uncertainty-aware value models that incorporate uncertainty into predictions, and (2) an uncertainty-aware selection process using the proposed efficient Group Thompson Sampling algorithm. Experiments on GSM8K show that our method mitigates search scaling flaws, achieving 90.5% coverage at 16 samples compared to 85.8% for conventional value-guided search. This work establishes the first systematic integration of uncertainty quantification in LLM search paradigms.

In an effort to lower the barrier to entry in underwater manipulation, this paper presents an open-source, user-friendly framework for bimanual teleoperation of a light-duty underwater vehicle-manipulator system (UVMS). This framework allows for the control of the vehicle along with two manipulators and their end-effectors using two low-cost haptic devices. The UVMS kinematics are derived in order to create an independent resolved motion rate controller for each manipulator, which optimally controls the joint positions to achieve a desired end-effector pose. This desired pose is computed in real-time using a teleoperation controller developed to process the dual haptic device input from the user. A physics-based simulation environment is used to implement this framework for two example tasks as well as provide data for error analysis of user commands. The first task illustrates the functionality of the framework through motion control of the vehicle and manipulators using only the haptic devices. The second task is to grasp an object using both manipulators simultaneously, demonstrating precision and coordination using the framework. The framework code is available at https://github.com/stevens-armlab/uvms_bimanual_sim.

Scientists at the University of Vermont and Tufts University used a supercomputer to evolve a design for tiny living robots made out of frog cells, then assembled them. The tiny new creatures did what they were supposed to do --make their way across a Petri dish. They also had some surprises for the researchers. "These are novel living machines," Joshua Bongard, a computer scientist and robotics expert at the University of Vermont who co-led the new research, said in a statement. "They're neither a traditional robot nor a known species of animal. The research results were published Monday in the Proceedings of the National Academy of Sciences. The first author was UVM doctoral student Sam Kriegman. The new "biobots" were designed on the Deep Green supercomputer cluster at UVM's Vermont Advanced Computing Core. Bongard said that in 100 runs, the supercomputer considered billions of designs, looking for a design for a creature that would travel across the bottom of a Petri dish as quickly as possible. "The design we built wasn't imagined by a human.

The industry and users have a love/hate relationship with UVM. It has quickly risen to become the most used verification methodology and yet at the same time it is seen as being overly complex, unwieldy and difficult to learn. The third day of DAC gets started with breakfast with Accellera to discuss UVM and what we can expect to see in the next 5 years. The discussion was led by Tom Alsop, principle engineer at Intel. Alsop's first question to the panelists was, where do you see UVM in the next 5 years?

The industry and users have a love/hate relationship with UVM. It has quickly risen to become the most used verification methodology and yet at the same time it is seen as being overly complex, unwieldy and difficult to learn. The third day of DAC gets started with breakfast with Accellera to discuss UVM and what we can expect to see in the next 5 years. The discussion was led by Tom Alsop, principle engineer at Intel. Alsop's first question to the panelists was, where do you see UVM in the next 5 years?

Characteristic models are an alternative, model based, representation for Horn expressions. It has been shown that these two representations are incomparable and each has its advantages over the other. It is therefore natural to ask what is the cost of translating, back and forth, between these representations. Interestingly, the same translation questions arise in database theory, where it has applications to the design of relational databases. This paper studies the computational complexity of these problems. Our main result is that the two translation problems are equivalent under polynomial reductions, and that they are equivalent to the corresponding decision problem. Namely, translating is equivalent to deciding whether a given set of models is the set of characteristic models for a given Horn expression. We also relate these problems to the hypergraph transversal problem, a well known problem which is related to other applications in AI and for which no polynomial time algorithm is known. It is shown that in general our translation problems are at least as hard as the hypergraph transversal problem, and in a special case they are equivalent to it.