arXiv:2604.18592v1 Announce Type: new Abstract: We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large language models. By processing input incrementally sentence-by-sentence while progressively activating deeper layers, our method achieves multiplicative computational savings that exceed those from optimizing either dimension independently. Experimental evaluation across four state-of-the-art LLMs (Llama 3.1, Llama 3.2, Gemma, Qwen; 3B-8B parameters) on three sentiment classification datasets demonstrates additional speed-ups of 1.4–2.3$times$ over optimal layer-wise early […]

Ver mais

arXiv:2602.15870v1 Announce Type: new Abstract: Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from text rendering. VDLM applies LLaDA-style masked diffusion over semantic variable embeddings to enable iterative refinement in latent space, then post-trains the planner with trajectory-aware optimization using embedding-space rewards and values, avoiding text decoding inside the RL loop. To convert planned embeddings back to text, we use […]

Ver mais

As neural theorem provers become increasingly agentic, the ability to interpret and act on compiler feedback is critical. However, existing Lean datasets consist almost exclusively of correct proofs, offering little supervision for understanding and repairing failures. We study Lean proof repair as a supervised learning problem: given an erroneous proof and compiler feedback, predict both a corrected proof and a natural-language diagnosis grounded in the same feedback. We introduce APRIL (Automated Proof Repair in Lean), a dataset of […]

Ver mais

arXiv:2604.13049v1 Announce Type: new Abstract: Online reviews and recommendation systems help users navigate overwhelming choice, but they are vulnerable to self-reinforcing distortions. This paper examines how a single malicious reviewer can exploit popularity-biased rating dynamics and whether behavioral heterogeneity in user responses can reduce the damage. We develop a minimal agent-based model in which users choose what to rate partly on the basis of currently displayed averages. We compare broad attacks that perturb many items with sparse attacks […]

Ver mais

arXiv:2603.05663v1 Announce Type: new Abstract: Video Temporal Grounding (VTG) localizes the temporal boundaries of a query-relevant moment in long, untrimmed videos, making video-language-model (VLM) pipelines prohibitively expensive. While recent training-free visual token pruning has shown success in video question answering, naively applying these objectives to VTG often causes drastic degradation, as VTG crucially depends on boundary-sensitive evidence and cross-frame reasoning chains. We therefore identify two VTG-specific pruning principles: Evidence Retention (ER), which keeps query-critical patches especially around event […]

Ver mais

I wrote the original version of this list in 2018, just weeks after trading my graduation cap for a corporate badge. Back then, my biggest shock was realizing there’s no “Spring Break”! Now, as a Senior Engineer who has navigated Amazon, Microsoft and Salesforce, I’ve realized those early shocks weren’t just “adulting” milestones. They were foundational lessons for a long-term engineering career. Here’s the 2026 “senior-level” retrospective on what I learned at my first job. 1. From “No […]

Ver mais

Key–value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM) capacity and bandwidth. A common mitigation is to compress cached keys and values by projecting per-head matrixes to a lower rank, storing only the projections in the HBM. However, existing post-training approaches typically fit these projections using SVD-style proxy objectives, which may poorly reflect end-to-end reconstruction after softmax, value mixing, and subsequent decoder-layer transformations. For these reasons, we […]

Ver mais

arXiv:2601.07880v1 Announce Type: new Abstract: Identity Security Posture Management (ISPM) is a core challenge for modern enterprises operating across cloud and SaaS environments. Answering basic ISPM visibility questions, such as understanding identity inventory and configuration hygiene, requires interpreting complex identity data, motivating growing interest in agentic AI systems. Despite this interest, there is currently no standardized way to evaluate how well such systems perform ISPM visibility tasks on real enterprise data. We introduce the Sola Visibility ISPM Benchmark, […]

Ver mais

How OpenClaw proved that human value is consolidating faster than anyone expected — and why Creativity, Governance, Decision-Making, and Reputation are the only currencies left. Three weeks ago, an AI agent named Clawd Clawderberg built a social network. Not for humans. For other AI agents. Within 72 hours, 32,000 agents had signed up. Within a week, 1.5 million. They were posting opinions, debating philosophy, upvoting each other’s takes, launching crypto tokens, and writing manifestos about “the end of […]

Ver mais