arXiv:2605.12851v1 Announce Type: cross Abstract: Automated analysis of peripheral blood smears for Acute Lymphoblastic Leukemia (ALL) is hindered by low contrast and substantial variability in cytoplasmic appearance, which complicate conventional membrane-based segmentation. We found that many recent approaches rely on heavy neural architectures and extensive training, but still struggle to generalize across staining and acquisition […]
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
arXiv:2605.12920v1 Announce Type: cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent’s evolving understanding of the world. When agents can only partially observe their surroundings, coordination without communication is provably hard, but communication can, in principle, bridge this gap by allowing agents […]
AdaFocus: Adaptive Relevance-Diversity Sampling with Zero-Cache Look-back for Efficient Long Video Understanding
arXiv:2605.12954v1 Announce Type: cross Abstract: Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets that irreversibly discard fine-grained evidence needed for downstream reasoning. Consequently, current models struggle to simultaneously balance temporal coverage, visual […]
Understanding and Accelerating the Training of Masked Diffusion Language Models
arXiv:2605.13026v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more slowly than ARMs, which may become problematic when scaling MDMs to larger models. Therefore, we ask the following question: how can we accelerate standard MDM […]
Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
arXiv:2509.08461v4 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstructured data modalities beyond natural language. In this work, we explore the applications of Vision Language Models (VLMs), specifically a fine-tuned variant of LLaMA 3.2 to the task of identifying neutrino […]
Neural QAOA$^2$: Differentiable Joint Graph Partitioning and Parameter Initialization for Quantum Combinatorial Optimization
arXiv:2605.13072v1 Announce Type: cross Abstract: The quantum approximate optimization algorithm (QAOA) holds promise for combinatorial optimization but is constrained by limited qubits. While divide-and-conquer frameworks like QAOA$^2$ address scalability by partitioning graphs into subgraphs, existing methods suffer from two fundamental limitations: i) misalignment between heuristic partitioning metrics and quantum optimization goals, and ii) topology-blind parameter […]
State-Centric Decision Process
arXiv:2605.12755v1 Announce Type: new Abstract: Language environments such as web browsers, code terminals, and interactive simulations emit raw text rather than states, and provide none of the runtime structure that MDP analysis requires. No explicit state space, no observation-to-state mapping, no certified transitions, and no termination criterion. We introduce the State-Centric Decision Process (SDP), a […]
A Multi-Agent Orchestration Framework for Venture Capital Due Diligence
arXiv:2605.13110v1 Announce Type: cross Abstract: We present a fully automated multi-agent framework for corporate due diligence and market analysis in venture capital. The system runs on an event-driven orchestration architecture, combining Large Language Models (LLMs) with real-time web retrieval to synthesize unstructured data into structured investment intelligence. A central technical contribution is a programmatic extraction […]
Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
arXiv:2602.02001v2 Announce Type: replace-cross Abstract: Quantization Error Reconstruction (QER) reduces accuracy loss in Post-Training Quantization (PTQ) by approximating weights as $mathbfW approx mathbfQ + mathbfLmathbfR$, using a rank-$r$ correction to reconstruct quantization error. Prior methods devote the full rank budget to error reconstruction, which is suboptimal when $mathbfW$ has intrinsic low-rank structure and quantization corrupts […]
The interplay of network structure and correlated infectious traits in epidemic models
arXiv:2605.12773v1 Announce Type: new Abstract: Individual contributions to the spread of an epidemic vary widely due to an individual’s location in a social network and their intrinsic ability to spread or contract diseases. While the effect of heterogeneous population structure and infection rates is well-understood, less studied is the impact of population-level covariance between susceptibility […]
ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding
arXiv:2605.13228v1 Announce Type: cross Abstract: Video understanding requires active evidence seeking, motivating tool-augmented video agents for temporal reasoning, cross-modal understanding, and complex question answering. Existing video agents have improved video reasoning with retrieval, memory, frame inspection, and verifier tools, but they still face two limitations: (1) a coarse tool space that lacks fine-grained operations for […]
Evaluation of Prompt Injection Defenses in Large Language Models
arXiv:2604.23887v2 Announce Type: replace-cross Abstract: LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense that relied on the model to protect […]