Reliable Chain-of-Thought via Prefix Consistency
arXiv:2605.07654v1 Announce Type: cross Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority
Knowledge catalogue
arXiv:2605.07654v1 Announce Type: cross Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority
arXiv:2605.07379v1 Announce Type: cross Abstract: Conventional visual object trackers localize targets using handcrafted spatial priors, often in the form of heatmaps. Such priors provide only surroga
arXiv:2605.06298v2 Announce Type: replace-cross Abstract: Training world models on vast quantities of unlabelled videos is a critical step toward fully autonomous intelligence. However, the prevailing
arXiv:2511.06571v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their internal mechanisms remain largely opaque. In t
arXiv:2605.07174v1 Announce Type: new Abstract: We study the problem of deceptive path planning (DPP), where an agent aims to conceal its true destination from external observers. While existing work
arXiv:2601.16130v2 Announce Type: replace-cross Abstract: Motivated reasoning - the idea that individuals processing information may be motivated to either arrive at accurate beliefs or arrive at desi
reply to Hinton’s reply to me, for additional context: Dear @geoffreyhinton, I literally never said that AI systems “JUST regurgitate”; that’s plainly false. I don’t believe it, and I didn’t say it. (
Artificial intelligence chipmaker Cerebras Systems Inc. is expected to increase the size and price of its initial public offering later today as investor demand for access to its shares continues to r
arXiv:2510.00568v3 Announce Type: replace Abstract: Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement l
arXiv:2605.07263v1 Announce Type: cross Abstract: Over-the-air federated learning (OTA-FL) reduces uplink latency by exploiting waveform superposition, but conventional analog aggregation schemes typi
arXiv:2605.07575v1 Announce Type: cross Abstract: Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall sho
arXiv:2605.06987v1 Announce Type: new Abstract: Aligning large language models (LLMs) to human preferences typically relies on aggregating pooled feedback into a single reward model. However, this sta
This Databricks resource examines retail markdown optimization strategies, contrasting reactive markdown approaches (responding to inventory issues after they occur) with proactive markdown strategies
arXiv:2605.08000v1 Announce Type: new Abstract: Recent progress in dense optical flow has been driven by increasingly complex architectures and multi-step refinement for test-time scaling. While these
arXiv:2605.07307v1 Announce Type: new Abstract: Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must
arXiv:2605.07164v1 Announce Type: new Abstract: Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is const
arXiv:2605.07331v1 Announce Type: cross Abstract: Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Cen
arXiv:2605.07755v1 Announce Type: cross Abstract: The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretical
arXiv:2602.04556v2 Announce Type: replace Abstract: Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output pr
arXiv:2605.06173v2 Announce Type: replace-cross Abstract: Diabetic Retinopathy (DR) is a leading cause of preventable blindness among working-age adults worldwide, yet most automated screening systems
arXiv:2605.05806v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decode
arXiv:2602.11162v2 Announce Type: replace Abstract: Recent studies have identified 'retrieval heads' in Large Language Models (LLMs) responsible for extracting information from input contexts. However
arXiv:2605.07106v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence int
arXiv:2605.06764v1 Announce Type: cross Abstract: Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, holds the promise of
arXiv:2605.07588v1 Announce Type: cross Abstract: Transformer blocks typically combine multi-head attention (MHA) for token mixing with gated MLPs for token-wise feature transformation, yet many choic
arXiv:2602.16548v2 Announce Type: replace Abstract: The inverse design of RNA three-dimensional (3D) structures is crucial for engineering functional RNAs in synthetic biology and therapeutics. While
arXiv:2605.07413v1 Announce Type: new Abstract: Obtaining accurate class labels is often costly or unreliable, and may also be limited by privacy or other practical conditions. Compared with asking an
arXiv:2602.19974v2 Announce Type: replace Abstract: Recent advancements in image generation have achieved impressive results in producing high-quality images. However, existing image generation models
arXiv:2510.24736v3 Announce Type: replace-cross Abstract: Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains ch
arXiv:2605.07752v1 Announce Type: new Abstract: Semiconductor materials manufacturing presents unique challenges for machine learning deployment due to evolving process conditions, equipment degradati
arXiv:2605.07634v1 Announce Type: cross Abstract: We consider a first order stochastic optimization framework where, at each iteration, K independent identically distributed (i.i.d.) data point sample
arXiv:2602.01372v2 Announce Type: replace-cross Abstract: Entropic regularization provides a simple way to approximate linear programs whose constraints split into two or more tractable blocks. The re
arXiv:2605.06686v1 Announce Type: new Abstract: Previous research has investigated the potential of refugee matching for boosting refugee outcomes, first considered by Bansak et al. (2018). This paper
arXiv:2605.06947v1 Announce Type: new Abstract: While autoregressive models have advanced 3D generation, creating physically stable brick structures remains a challenge due to the strict requirements
arXiv:2605.07129v1 Announce Type: cross Abstract: Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and
arXiv:2605.07396v1 Announce Type: cross Abstract: On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box sce
arXiv:2605.08061v1 Announce Type: new Abstract: We argue that decomposing reward into weighted, verifiable criteria and using an LLM judge to score them provides a partial-credit optimization signal:
arXiv:2605.07760v1 Announce Type: new Abstract: Platform content moderation applies explicit policy rules and context-dependent conditions to decide whether user content is allowed, restricted, or rem
arXiv:2601.01285v2 Announce Type: replace Abstract: Medical image segmentation requires balancing local precision for boundary-critical clinical applications, global context for anatomical coherence,
arXiv:2503.05085v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have fundamentally reshaped speech-to-speech (S2S) systems, enabling increasingly natural spoken int
arXiv:2605.06230v2 Announce Type: replace Abstract: As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool
arXiv:2605.07630v1 Announce Type: cross Abstract: When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may b
arXiv:2605.05995v2 Announce Type: replace-cross Abstract: The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constrain
arXiv:2605.07102v1 Announce Type: new Abstract: Evaluating literary quality requires assessing interpretive dimensions such as cultural representation, emotional depth, and philosophical sophisticatio
arXiv:2605.05693v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most exis
arXiv:2605.07604v1 Announce Type: cross Abstract: 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scene
arXiv:2605.07212v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a cornerstone of brain-computer interfaces and clinical neuroscience, yet deep learning models are typically trained a
arXiv:2605.06908v1 Announce Type: cross Abstract: Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidenc
arXiv:2605.07239v1 Announce Type: new Abstract: We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect t
Dua Lipa filed a $15 million lawsuit against Samsung, alleging the electronics company used her photograph to sell televisions without permission or payment. Samsung began featuring Lipa's image on TV
arXiv:2605.07800v1 Announce Type: new Abstract: Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions spe
Sarra builds apps with her two sons. Noni shipped Bamboo Brain into the App Store's top 12 in Education. Rebecca built the system she wished she'd had during her custody battle. To every mother buildi
arXiv:2605.07264v1 Announce Type: new Abstract: Accurate Digital Surface Model (DSM) reconstruction from satellite imagery is critical for applications such as disaster response, urban planning, and l
arXiv:2605.07181v1 Announce Type: new Abstract: Sparse-view satellite image surface reconstruction remains highly challenging, fundamentally because the reliability of multi-view matching under satell
arXiv:2511.16520v2 Announce Type: replace-cross Abstract: Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific
arXiv:2512.23770v3 Announce Type: replace-cross Abstract: In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tas
arXiv:2508.15989v2 Announce Type: replace Abstract: Equilibrium Propagation (EP) is a biologically inspired local learning rule first proposed for convergent recurrent neural networks (CRNNs), in whic
arXiv:2509.00338v3 Announce Type: replace-cross Abstract: Hierarchical reinforcement learning (RL) has the potential to enable effective decision-making over long timescales. Existing approaches, whil
arXiv:2605.07820v1 Announce Type: new Abstract: Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they u
arXiv:2602.03473v2 Announce Type: replace-cross Abstract: Continual learning, especially class-incremental learning (CIL), on the basis of a pre-trained model (PTM) has garnered substantial research i